fynsight: MCP server for DATEV is an MCP server published by de.fynsight, hosted at mcp.fynsight.de. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 29 tools, including get_all_accounts, compute_aggregates, get_periodic_summaries, search_cost_center_transactions, get_cost_center_list.
DATEV financial data for AI assistants: P&L, KPIs, bookings, budgets and monthly reporting.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Lists the tenant's accounts with label, category, sub_account, account_ref ("8400" or "8400/130", the notation of the accounts filters in other tools), is_pnl_account, is_revenue_account and knw_row_number. Each sub-account is its own row. Categories are the tenant's own P&L labels and balance-sheet categories. Filters: exact category, account number range (account_from/account_to) and is_pnl (P&L vs. balance sheet accounts). Without limit every matching account is returned (paginated internally, no row cap); with limit the response reports limit and truncated=true when more accounts exist.
| Parameter | Type | Description |
|---|---|---|
| limit | number | Optional cap on the number of accounts returned (positive integer). Omit it to get every matching account. With a limit the query itself is bounded and the response's 'truncated' field says whether more accounts existed beyond the cap. |
| is_pnl | boolean | Filter by P&L accounts (true) or balance sheet accounts (false) |
| category | string | Filter by exact category name (e.g. 'Umsatzerlöse', 'Bank') |
| account_to | number | Maximum account number (inclusive) |
| account_from | number | Minimum account number (inclusive) |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "get_all_accounts",
"description": "Lists the tenant's accounts with label, category, sub_account, account_ref (\"8400\" or \"8400/130\", the notation of the accounts filters in other tools), is_pnl_account, is_revenue_account and knw_row_number. Each sub-account is its own row. Categories are the tenant's own P&L labels and balance-sheet categories. Filters: exact category, account number range (account_from/account_to) and is_pnl (P&L vs. balance sheet accounts). Without limit every matching account is returned (paginated internally, no row cap); with limit the response reports limit and truncated=true when more accounts exist.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "number",
"description": "Optional cap on the number of accounts returned (positive integer). Omit it to get every matching account. With a limit the query itself is bounded and the response's 'truncated' field says whether more accounts existed beyond the cap."
},
"is_pnl": {
"type": "boolean",
"description": "Filter by P&L accounts (true) or balance sheet accounts (false)"
},
"category": {
"type": "string",
"description": "Filter by exact category name (e.g. 'Umsatzerlöse', 'Bank')"
},
"account_to": {
"type": "number",
"description": "Maximum account number (inclusive)"
},
"account_from": {
"type": "number",
"description": "Minimum account number (inclusive)"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Konten auflisten",
"readOnlyHint": true,
"openWorldHint": false
}
}Aggregates bookings and account balances (sum, avg, mom, yoy, cumulative, share, count) by period, cost center, account or category. Amounts are ledger amounts (sign_convention "ledger", see sign_convention_note): revenue and expense are both positive as booked, a negative value reduces the account. Sums are therefore not result figures; get_periodic_summaries and aggregate_pnl_by_cost_center return the result effect (revenue +, expense −). A group that contains revenue and expense accounts has mixes_revenue_and_expense=true, and the response adds a warning. With group_by=account every sub-account is its own group; the group key carries account, sub_account (null = none) and account_ref. totals.sum covers all periods in scope regardless of granularity. mom/yoy compare with the previous bucket inside the requested window; the calendar previous month comes from get_periodic_summaries with include_previous. Groups are paged via after_group and pagination.next_cursor. available_range gives the tenant's full data range; an empty page does not mean there is no data. scope.pnl_reconciled=true means each month was cross-checked against the P&L; a warning then names period, both amounts and the difference. With text_query, cost_centers or categories the result is a subset by design and not reconciled. With text_query, scope.text_match gives matched_sum, unfiltered_sum (same accounts, cost centers and months without the search term) and matched_share_pct.
| Parameter | Type | Description |
|---|---|---|
| periods | array | Months as YYYY-MM. The shorthands 'YYYY' and 'YYYY-Qn' (e.g. '2023', '2023-Q2') expand to exactly the months the tenant has data for. Omit for every available period. |
| accounts | array | Accounts as "8400" (main account, same as "8400/000") or "8400/130" (sub-account). Each entry matches exactly that variant ("8400" excludes "8400/130"); unknown accounts are rejected. This is the account_ref notation of get_all_accounts and of the compute_aggregates groups. |
| group_by | array | Grouping dimensions |
| categories | array |
P&L summaries per period: metrics (EBIT, EBITDA, margins, depreciation, financial, tax) and category_totals, as result effect (revenue +, expense −). Each summary's metrics.category_totals_sort_order gives the GuV-Explorer display order per category (lower sorts first). granularity quarter, year or total sums the months in the tool and re-derives the metrics. Per-account balances are omitted by default; include_account_totals=true adds `totals` per summary. include_previous compares each summary with its CALENDAR predecessor (loaded automatically; granularity total has none): previous_period, previous_comparison (per headline figure: current, previous, delta_absolute, delta_percentage) and delta_category_totals (same keys as category_totals, with label_ids, current, previous and the deltas). A category without bookings in a period that has computed metrics counts as 0, not null; delta_percentage is null when the previous value is 0. All deltas are null (not 0) when a side has no computed metrics. For quarter/year, if the bucket or its predecessor covers fewer months than the bucket length (3/12; see months_covered and previous_months_covered), all deltas are null and a warning names the period. Every response carries available_range ({from, to}, YYYY-MM); requested months without a ledger row are listed in missing_periods and named in a warning. An invalid period such as 2026-13 is rejected.
| Parameter | Type | Description |
|---|---|---|
| date_to | string | End of a date range (YYYY-MM-DD or YYYY-MM), additive to `periods`. Independent of date_from — given alone, the range starts at the tenant's first available period. Omit both for all data. |
| periods | array | Months as YYYY-MM |
| date_from | string | Start of a date range (YYYY-MM-DD or YYYY-MM), additive to `periods`. Independent of date_to — given alone, the range runs through the tenant's last available period. Omit both for all data. |
| granularity | string | Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself. |
Searches individual bookings. Each row has period, cost_center, account, sub_account, contra_account, contra_sub_account (null if none), amount, description, transaction_date (day-exact booking date), `id` (the transaction_id for propose-transaction-correction) and `source` ("upload" or "manual"), plus correction_status ("none" | "pending" | "corrected") and correction_role (null | "reversal" | "rebooking"): whether a booking has an open or approved correction, or is itself the reversal/re-booking line of one. accounts takes "8400" (main account) or "8400/130"; each entry matches exactly that variant and unknown accounts are rejected. text_query is a case-insensitive substring of description OR reference; % and _ are searched as characters, not as wildcards. limit_count is a whole number of at least 1 (default 200, values above 1000 are capped at 1000; anything else is rejected). With truncated=true more bookings match than were returned; beyond 1000 only narrowing the filters helps. available_range gives the tenant's data range. With group_by the response carries `groups` (by period and/or cost center, each with transaction_count and transactions_truncated) instead of `rows`. Counts are reported in total_count (returned bookings), group_count (groups) and transaction_count per group; limit_count is a cap, not a count. The tool returns single bookings; sums per month, cost center or account come from compute_aggregates.
| Parameter | Type | Description |
|---|---|---|
| date_to | string | Day-exact upper bound on transaction_date, inclusive (YYYY-MM-DD). Omit for no upper bound. |
| periods | array | Months as YYYY-MM. Omit for every available period. |
| accounts | array | Accounts as "8400" (main account, same as "8400/000") or "8400/130" (sub-account). Each entry matches exactly that variant ("8400" excludes "8400/130"); unknown accounts are rejected. This is the account_ref notation of get_all_accounts and of the compute_aggregates groups. |
| group_by | array | Optional. Groups the bookings by these fields; the response then carries `groups` instead of `rows`. |
Lists all cost centers of the tenant with id and name, plus total_count and hidden_count. Rows carry `hidden: true` when the tenant has hidden that cost center in the app; it still holds bookings and still counts towards company-wide figures, but is no longer selectable.
| Parameter | Type | Description |
|---|---|---|
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "get_cost_center_list",
"description": "Lists all cost centers of the tenant with id and name, plus total_count and hidden_count. Rows carry `hidden: true` when the tenant has hidden that cost center in the app; it still holds bookings and still counts towards company-wide figures, but is no longer selectable.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Kostenstellen auflisten",
"readOnlyHint": true,
"openWorldHint": false
}
}P&L metrics per cost center and period across the full history, paginated over cost_center via after_cost_center and pagination.next_cursor (with categories each row counts several times against the page budget; the response states the weight). Amounts are result effect (revenue +, expense −). `revenue` is the sum of all labels in the tenant's revenue group; sales deductions and penalties booked on revenue-group labels are already netted in. include_categories=true adds the split per label (category_totals), and revenue is then the sum of the revenue-group categories. granularity quarter, year or total returns the finished rolled-up figures. available_range gives the overall time range. Hidden cost centers stay included and are marked as hidden on each row. Every number in cost_centers must be a known cost center (unknown numbers are rejected); a known cost center without P&L bookings in the range is listed in `warnings`. period_from/period_to must be valid (YYYY-MM or YYYY-MM-DD) and period_from must not be after period_to.
| Parameter | Type | Description |
|---|---|---|
| metrics | array | Which metrics to return (default: all six) |
| period_to | string | End period YYYY-MM or YYYY-MM-DD (optional) |
| granularity | string | Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself. |
| period_from | string | Start period YYYY-MM or YYYY-MM-DD (optional) |
| cost_centers | array | Optional cost center numbers; get_cost_center_list maps names to numbers. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
Lists the tenant's budget plans with id (the plan_id that get_budget_vs_actual takes), name, year, version, status and type, optionally filtered by year and status.
| Parameter | Type | Description |
|---|---|---|
| year | number | Filter by year (e.g. 2025). Omit for all years. |
| status | string | Filter by status. Omit for all. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "list_budget_plans",
"description": "Lists the tenant's budget plans with id (the plan_id that get_budget_vs_actual takes), name, year, version, status and type, optionally filtered by year and status.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"year": {
"type": "number",
"description": "Filter by year (e.g. 2025). Omit for all years."
},
"status": {
"enum": [
"draft",
"active",
"archived"
],
"type": "string",
"description": "Filter by status. Omit for all."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Budgetpläne auflisten",
"readOnlyHint": true,
"openWorldHint": false
}
}Budget (Soll) vs. actual (Ist) with variance and YTD summary for one plan (plan_id from list_budget_plans). detail=summary omits period_rows and row_count. Besides the per-category rows (period_rows, ytd_summary) the response carries derived P&L metrics for plan and actual: `metrics` (per period) and `metrics_ytd` (all periods of the response) with revenue, other_income, cogs, opex, depreciation, financial, tax, gross_margin, ebitda, ebit, ebt and net_income (= Jahresueberschuss), each with budget, actual, variance and variance_pct. They are computed from tenant_config.pnl_labels exactly like get_periodic_summaries.metrics. `unmapped_categories` lists categories with amounts but no subtotal_group (not part of any metric). With cost_center set, actuals of the metrics are tenant-wide (see metrics_note). Account level (granularity=account): one row per account/sub-account of the plan, key "8400" (the main account = sub-account 000, compared against the actuals of the main account only) or "8400/130" (a specific sub-account, compared against that sub-account only); the two never overlap and are not summed. All granularities (category, account and BAB row) use the result view: revenue positive, expense negative, plan and actual alike (budget plans stored with positive expenses are normalized), so the account rows of a category add up to that category's value and a positive variance always means better for the result.
| Parameter | Type | Description |
|---|---|---|
| detail | string | rows (default): full period_rows + row_count; summary: only ytd_summary, metrics, metrics_ytd and unmapped_categories. |
| date_to | string | End date YYYY-MM-DD or YYYY-MM. Omit for full plan range. |
| plan_id * | string | UUID of the budget plan (the id from list_budget_plans) |
| date_from | string | Start date YYYY-MM-DD or YYYY-MM. Omit for full plan range. |
| cost_center |
Calculates the values of the tenant's active KPIs for a period: value, unit, format_type, previous_value, change and change_percentage (month-over-month change) and positive_trend_is_good per KPI.
| Parameter | Type | Description |
|---|---|---|
| period * | string | Accounting period in YYYY-MM format (e.g. '2025-03') |
| kpi_ids | array | Optional list of KPI IDs to filter. Omit for all active KPIs. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
| include_previous | boolean | Include previous-period comparison (default true) |
{
"name": "query_kpis",
"description": "Calculates the values of the tenant's active KPIs for a period: value, unit, format_type, previous_value, change and change_percentage (month-over-month change) and positive_trend_is_good per KPI.",
"inputSchema": {
"type": "object",
"required": [
"period"
],
"properties": {
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])$",
"description": "Accounting period in YYYY-MM format (e.g. '2025-03')"
},
"kpi_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional list of KPI IDs to filter. Omit for all active KPIs."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
},
"include_previous": {
"type": "boolean",
"description": "Include previous-period comparison (default true)"
}
}
},
"annotations": {
"title": "KPIs abfragen",
"readOnlyHint": true,
"openWorldHint": false
}
}Time series of a single named metric across periods, with month-over-month and year-over-year change per point (value, change, change_percentage, yoy_change, yoy_change_percentage, compared_period). The metric is one bucket (revenue, other_income, cogs, opex, depreciation, financial, tax), one derived P&L aggregate (gross_margin, ebitda, ebit, ebt, net_income) or one P&L category from tenant_config.pnl_labels. get_periodic_summaries returns all metrics of a period at once (including sort_order and include_previous); compute_aggregates covers account/cost-center/category sums with grouping, share or cumulative but cannot compute the derived aggregates (ebitda etc.). Time range: `periods` (a count of the most recent periods, default 12) or `date_from`/`date_to`; not a period list as in other tools.
| Parameter | Type | Description |
|---|---|---|
| metric * | string | Metric name: one of "revenue", "other_income", "cogs", "opex", "depreciation", "financial", "tax" (buckets) or "gross_margin", "ebitda", "ebit", "ebt", "net_income" (aggregates), or any P&L category name from tenant_config.pnl_labels. |
| date_to | string | Alternative to `periods`: end of a date range (YYYY-MM-DD or YYYY-MM), independent of date_from. |
| periods | number | Number of most recent periods to include (default 12). A count, not a period list. |
| date_from | string | Alternative to `periods`: start of a date range (YYYY-MM-DD or YYYY-MM), independent of date_to. |
| granularity | string | Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
Generates a structured financial report as JSON. Pass either period (one month) or date_from/date_to (a range), never both; invalid or contradictory values are rejected with an error. report_type=pnl: the P&L lines of the period or range as one list ordered by period, without a period argument ALL months (a long history can be large). report_type=category-breakdown: summary figures and category totals. Default is the latest month with data and the output carries one month. For a range of several months it returns months[] (one entry per month, each with summary, categories and category_totals) plus total (the sum of the months with summary re-derived from the summed buckets, not added up from the monthly summaries). report_type=kpi-dashboard: the KPI values with change against the previous month. Default is the latest month with data; for a range of several months it returns months[] with the KPIs of each month, at most 12 months per call (more is rejected). category-breakdown and kpi-dashboard answer with an error naming the available data range when the period or range has no data; in a multi-month range, months without data are listed in missing_periods.
| Parameter | Type | Description |
|---|---|---|
| period | string | One month (YYYY-MM). Use either period or date_from/date_to, not both. Without any time argument: pnl returns all months, category-breakdown and kpi-dashboard the latest month with data. |
| date_to | string | End of a range (YYYY-MM-DD or YYYY-MM). Optional on its own: the range then ends at the last month with data. Not allowed together with period; must not be before date_from. |
| date_from | string | Start of a range (YYYY-MM-DD or YYYY-MM). Optional on its own: the range then starts at the first month with data. Not allowed together with period. |
| report_type * | string | Type of report to generate |
| organization_id |
Creates a new budget plan. The version is incremented automatically for plans with the same name and year. A plan with type=forecast holds the ACTUAL values of the already closed months plus the forecast for the remaining months of the year; otherwise year and YTD comparisons against actuals are wrong. The closed months can be read via get_periodic_summaries (category_totals) and are loaded together with the forecast via upload-budget-entries as category entries.
| Parameter | Type | Description |
|---|---|---|
| name * | string | Plan name (e.g. "Jahresplan 2025") |
| type | string | Plan type (default: budget) |
| year * | number | Planning year (e.g. 2025) |
| description | string | Optional description |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "create-budget-plan",
"description": "Creates a new budget plan. The version is incremented automatically for plans with the same name and year. A plan with type=forecast holds the ACTUAL values of the already closed months plus the forecast for the remaining months of the year; otherwise year and YTD comparisons against actuals are wrong. The closed months can be read via get_periodic_summaries (category_totals) and are loaded together with the forecast via upload-budget-entries as category entries.",
"inputSchema": {
"type": "object",
"required": [
"name",
"year"
],
"properties": {
"name": {
"type": "string",
"description": "Plan name (e.g. \"Jahresplan 2025\")"
},
"type": {
"enum": [
"budget",
"forecast",
"scenario"
],
"type": "string",
"description": "Plan type (default: budget)"
},
"year": {
"type": "number",
"description": "Planning year (e.g. 2025)"
},
"description": {
"type": "string",
"description": "Optional description"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Budgetplan anlegen",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Inserts or updates budget entries (monthly values) of a plan; a value that already exists for the same entry and month is overwritten. Exactly one of category, account or knw_row_number is set per entry. An account entry may name one sub-account as part of the account, e.g. "8400/130" (slash, as shown in the app); there is no separate sub_account parameter. The main account is sub-account 000: "8400" and "8400/000" mean the same and are compared against the actuals of the main account ONLY (not the sum of the sub-accounts; main-account and sub-account entries never overlap). If the account has no main account but exactly ONE sub-account, that one is used; with SEVERAL the entry is rejected (BUDGET_ACCOUNT_AMBIGUOUS, sub-accounts listed). A sub-account that does not exist for the tenant is rejected (BUDGET_ACCOUNT_UNKNOWN). An account unknown to the tenant is still accepted. Amounts are signed (expenses negative); plans created from a file upload that store expenses as positive magnitudes are rejected. For a forecast plan (type=forecast) the entries cover the ACTUAL values of the closed months plus the forecast of the remaining months (see create-budget-plan); without the closed months the year/YTD comparison is wrong. A category name that matches no P&L label is rejected with the list of valid category names and nothing is written.
| Parameter | Type | Description |
|---|---|---|
| entries * | array | Budget entries to upsert |
| plan_id * | string | UUID of the target budget plan |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
Proposes a manual correction booking (Korrekturbuchung) for a month, e.g. an unbooked invoice or an anomaly correction on a specific account and cost center. This does NOT post to the ledger: it creates a PENDING proposal that a human approves in the web app.
| Parameter | Type | Description |
|---|---|---|
| note | string | Optional internal note explaining the correction |
| amount * | number | Amount in the ledger sign convention: POSITIVE on an expense account books ADDITIONAL expense (an unbooked invoice is positive, never negative), POSITIVE on a revenue account books additional revenue. Use a NEGATIVE amount only to REDUCE a booked amount (e.g. moving cost off an account). |
| period * | string | Accounting month (YYYY-MM or YYYY-MM-DD) |
| account * | string | Account as shown in the app: "4321", or with sub-account "8400/130" (account/sub-account, slash). Without a sub-account the sub-account is resolved automatically when the account has exactly one variant; if there are several, the error lists the known variants. Must exist for the tenant. |
| cost_center * | number | Cost center / Kostenstelle number (e.g. 93) |
| description | string | Booking text, e.g. "Gies Dienstleistung" |
| contra_account | string | Optional contra account (Gegenkonto), same notation: "1200" or "1200/000". Any account the tenant knows: in its chart of accounts or already used as a contra account in its bookings (e.g. bank, personal or balance sheet accounts from a KNW import). A bare number resolves if the tenant knows exactly … |
Proposes a correction to an EXISTING ledger booking: wrong cost center, wrong account, wrong amount or wrong month. This does NOT change the original booking and does NOT post to the ledger: it creates a PENDING proposal that a human approves in the web app. On approval a reversal of the original booking plus a corrected re-booking are written. The transaction id is the `id` of a row from `search_cost_center_transactions`. A booking that does not exist yet is proposed with `propose-manual-adjustment`.
| Parameter | Type | Description |
|---|---|---|
| reason * | string | Why the booking is corrected; mandatory for the audit trail |
| new_amount | number | New amount, in the same sign convention as the original booking (positive = expense/revenue on that account) — only if the amount changes; 0 means the booking was a duplicate and is only reversed |
| new_period | string | New accounting month (YYYY-MM or YYYY-MM-DD) — only if the month changes |
| new_account | string | New account — only if the account or its sub-account changes. Notation "4321" or "8400/130". Without a sub-account it is resolved automatically when the account has exactly one variant (the old sub-account is never carried over); if there are several, pass the full account/sub-account. |
| transaction_id * | string | UUID of the existing booking, from `search_cost_center_transactions` |
| new_cost_center | number | New cost center / Kostenstelle — only if the cost center changes |
| organization_id | number |
Lists the tenant's manual correction bookings. status is one of pending, approved, rejected or superseded; period (YYYY-MM or YYYY-MM-DD) restricts the list to one month. Without filters all statuses are returned.
| Parameter | Type | Description |
|---|---|---|
| period | string | Filter by month (YYYY-MM or YYYY-MM-DD) |
| status | string | Filter by status: pending, approved, rejected or superseded |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "list-manual-adjustments",
"description": "Lists the tenant's manual correction bookings. status is one of pending, approved, rejected or superseded; period (YYYY-MM or YYYY-MM-DD) restricts the list to one month. Without filters all statuses are returned.",
"inputSchema": {
"type": "object",
"properties": {
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Filter by month (YYYY-MM or YYYY-MM-DD)"
},
"status": {
"enum": [
"pending",
"approved",
"rejected",
"superseded"
],
"type": "string",
"description": "Filter by status: pending, approved, rejected or superseded"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Korrekturvorschläge auflisten",
"readOnlyHint": true,
"openWorldHint": false
}
}Edits a PENDING manual correction proposal (amount, account, cost center, description, note, period). Approved bookings cannot be edited; they are deleted in the app.
| Parameter | Type | Description |
|---|---|---|
| id * | string | UUID of the pending proposal |
| note | string | New note |
| amount | number | New amount, in the ledger sign convention: POSITIVE on an expense account books additional expense, POSITIVE on a revenue account books additional revenue. Use a NEGATIVE amount only to REDUCE a booked amount. |
| period | string | New month (YYYY-MM or YYYY-MM-DD) |
| account | string | New account, "4321" or "8400/130". Without a sub-account it is resolved automatically when the account has exactly one variant; otherwise pass the full account/sub-account. |
| cost_center | number | New cost center |
| description | string | New booking text |
| contra_account | string | New contra account, same notation and rules as in propose-manual-adjustment. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
Withdraws (deletes) a PENDING manual correction proposal that has not been approved yet. Approved bookings are deleted in the app.
| Parameter | Type | Description |
|---|---|---|
| id * | string | UUID of the pending proposal to withdraw |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "withdraw-manual-adjustment",
"description": "Withdraws (deletes) a PENDING manual correction proposal that has not been approved yet. Approved bookings are deleted in the app.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "UUID of the pending proposal to withdraw"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Korrekturvorschlag zurückziehen",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}Returns the status of a Monatsreporting run (month-end close): its phase plus the number of open anomaly cases, open clarification questions and open follow_up checks (follow_ups_open). period (YYYY-MM) selects the active run of that month (not superseded or failed); without a run for it the answer says so. run_id takes precedence over period; with neither, the most recent run is returned. READ ONLY. A run is started with start-month-run; approving, publishing and closing happen only in the app.
| Parameter | Type | Description |
|---|---|---|
| period | string | Optional month, YYYY-MM: the active run of that month. |
| run_id | string | Optional UUID of the run. Takes precedence over period. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "get-month-run-status",
"description": "Returns the status of a Monatsreporting run (month-end close): its phase plus the number of open anomaly cases, open clarification questions and open follow_up checks (follow_ups_open). period (YYYY-MM) selects the active run of that month (not superseded or failed); without a run for it the answer says so. run_id takes precedence over period; with neither, the most recent run is returned. READ ONLY. A run is started with start-month-run; approving, publishing and closing happen only in the app.",
"inputSchema": {
"type": "object",
"properties": {
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])$",
"description": "Optional month, YYYY-MM: the active run of that month."
},
"run_id": {
"type": "string",
"description": "Optional UUID of the run. Takes precedence over period."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Status Monatsabschluss",
"readOnlyHint": true,
"openWorldHint": false
}
}Lists the anomaly cases of a Monatsreporting run: view summary (default) gives counts, sums and top cases, view cases lists single cases, filtered and paginated. status: open (default), decided (resolved/dismissed) or all. by_cost_center entries carry hidden (hidden in the app) and are never dropped. Amounts (actual, reference, delta = actual - reference, delta_pct) are taken unchanged from the detection rules; only budget_deviation and mom_outlier carry delta (sign_flip: actual = current, duplicate_suspicion: actual = amount, missing_account: no amount). sum_abs_delta is per kind, never mixed across kinds (null plus cases_without_delta for kinds without delta). commentary is the case note (Reporting-Vermerk): material for the comment of the position while the case is open, the short form of that comment once a person accepts it in the app. The report shows comments (list-comment-status), not case notes. commentary_source: ai = AI review, user = a person, null = older case. A follow_up case checks an earlier watch item: watch holds the original statement and the result (recurred true/false/null; position_missing true = position not assessable this month, which is not "did not recur"). Each case carries clarification (open or answered question with context, suggestions, answer) or null; the summary counts open_clarifications and follow_ups. updated_at is the last change of the case, not the decision time.
| Parameter | Type | Description |
|---|---|---|
| top | number | view summary: number of top cases (default 20, max 50) |
| kind | string | Filter by case kind |
| view | string | summary (default): counts, sums and top cases; cases: single cases, paginated |
| limit | number | view cases: page size (default 50, silently capped at 200) |
| run_id * | string | UUID of the run |
Records the answer to an open clarification question raised for an anomaly case. It does NOT approve any correction (corrections are approved in the app).
| Parameter | Type | Description |
|---|---|---|
| answer * | string | The answer (1–4000 chars) |
| suggestion_id | string | Optional: id of the suggestion of the question (clarification.suggestions[].id) that the answer is based on; the answer text is still required and stored as sent |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
| clarification_id * | string | UUID of the clarification question |
{
"name": "answer-clarification",
"description": "Records the answer to an open clarification question raised for an anomaly case. It does NOT approve any correction (corrections are approved in the app).",
"inputSchema": {
"type": "object",
"required": [
"clarification_id",
"answer"
],
"properties": {
"answer": {
"type": "string",
"description": "The answer (1–4000 chars)"
},
"suggestion_id": {
"type": "string",
"description": "Optional: id of the suggestion of the question (clarification.suggestions[].id) that the answer is based on; the answer text is still required and stored as sent"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
},
"clarification_id": {
"type": "string",
"description": "UUID of the clarification question"
}
}
},
"annotations": {
"title": "Rückfrage beantworten",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}For a Monatsreporting run, lists every P&L position and whether it is commented, has an AI draft, or is still open. Covers P&L lines, summary metrics, cost centers and the total, each with a shareable deeplink and the published/draft comment text (body). Optional filters target_type and state. READ ONLY.
| Parameter | Type | Description |
|---|---|---|
| state | string | Optional: only positions in this state. Counts refer to the filtered set; total_positions is unfiltered. |
| run_id * | string | UUID of the run |
| target_type | string | Optional: only positions of this type |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "list-comment-status",
"description": "For a Monatsreporting run, lists every P&L position and whether it is commented, has an AI draft, or is still open. Covers P&L lines, summary metrics, cost centers and the total, each with a shareable deeplink and the published/draft comment text (body). Optional filters target_type and state. READ ONLY.",
"inputSchema": {
"type": "object",
"required": [
"run_id"
],
"properties": {
"state": {
"enum": [
"commented",
"draft",
"open"
],
"type": "string",
"description": "Optional: only positions in this state. Counts refer to the filtered set; total_positions is unfiltered."
},
"run_id": {
"type": "string",
"description": "UUID of the run"
},
"target_type": {
"enum": [
"pnl_line",
"summary_metric",
"cost_center",
"total"
],
"type": "string",
"description": "Optional: only positions of this type"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Kommentarstatus",
"readOnlyHint": true,
"openWorldHint": false
}
}Result bridge for a month: EBITDA, EBIT and net income from a comparison value to actual, step by step per P&L category. READ ONLY. compare_to: previous_month, previous_quarter_month, previous_year or budget (plan_id optional, only with budget; default is the active plan of the year of the period, without one the call fails with NO_ACTIVE_BUDGET_PLAN). All amounts are result impact (revenue +, expense -, positive = improves the result; deltas = actual - comparison). start/end come from the computed metrics, the steps from category deltas, check.reconciles proves they add up (on unrounded values). unassigned = result change no category of this metric explains (labels without id or subtotal group, accounts without label); excluded lists what is left out (unlabeled_accounts, labels_without_group) and a warning appears when either is non-empty. rounding_difference = end - (start + steps + other + unassigned) on the rounded figures. Steps carry sort_order (P&L order) and auffaellig; the list is sorted by absolute delta. Small steps (below other_threshold, share of the absolute total change, default 0.05) are collapsed into other with their list.
| Parameter | Type | Description |
|---|---|---|
| period * | string | Month, YYYY-MM |
| plan_id | string | UUID of the budget plan; only with compare_to budget. Omitted: active plan of the year |
| compare_to * | string | Comparison value |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
| other_threshold | number | Share (0..0.5, default 0.05) of the absolute total change below which categories are collapsed into other |
Starts the Monatsreporting run (month-end close) for a month, only when that month has NO run yet (any status except failed/superseded counts, including signed-off months). Otherwise nothing is written and the existing run is returned with already_exists true, its status and a deeplink, so calling it twice is safe. It never replaces a run; restarting happens only in the app, with confirmation. The month must have booking data, otherwise NO_DATA_FOR_PERIOD is returned and no run is created. Starting normalizes the figures, collects anomaly cases and checks due watch items against them (no approval). Nothing runs in the background afterwards: AI reviews and comment drafts are created only when a person asks for them in the app. Follow-up tools: get-month-run-status, list-open-anomaly-cases.
| Parameter | Type | Description |
|---|---|---|
| period * | string | Month, YYYY-MM |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "start-month-run",
"description": "Starts the Monatsreporting run (month-end close) for a month, only when that month has NO run yet (any status except failed/superseded counts, including signed-off months). Otherwise nothing is written and the existing run is returned with already_exists true, its status and a deeplink, so calling it twice is safe. It never replaces a run; restarting happens only in the app, with confirmation. The month must have booking data, otherwise NO_DATA_FOR_PERIOD is returned and no run is created. Starting normalizes the figures, collects anomaly cases and checks due watch items against them (no approval). Nothing runs in the background afterwards: AI reviews and comment drafts are created only when a person asks for them in the app. Follow-up tools: get-month-run-status, list-open-anomaly-cases.",
"inputSchema": {
"type": "object",
"required": [
"period"
],
"properties": {
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])$",
"description": "Month, YYYY-MM"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Monatslauf starten",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Writes the reporting note (Reporting-Vermerk) of an open anomaly case, e.g. "one-off consulting invoice". The month report shows explanations, not case notes: once the case is decided in the app, the note becomes material from which the explanation draft of the position is written. It changes ONLY this note, never the case status; deciding a case (resolved/dismissed) happens in the app. A case that already has a note is rejected (CASE_NOTE_EXISTS, existing_note returned) unless replace is true, which overwrites the existing note. Only possible before the figures are approved (run status up to awaiting_approval); from approved on, and for decided cases, the call is rejected. The internal processing note is never touched.
| Parameter | Type | Description |
|---|---|---|
| note * | string | The explanation (1–8000 chars) |
| case_id * | string | UUID of the anomaly case |
| replace | boolean | Required true to overwrite an existing note; without it the call is rejected and the existing text stays. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "note-anomaly-case",
"description": "Writes the reporting note (Reporting-Vermerk) of an open anomaly case, e.g. \"one-off consulting invoice\". The month report shows explanations, not case notes: once the case is decided in the app, the note becomes material from which the explanation draft of the position is written. It changes ONLY this note, never the case status; deciding a case (resolved/dismissed) happens in the app. A case that already has a note is rejected (CASE_NOTE_EXISTS, existing_note returned) unless replace is true, which overwrites the existing note. Only possible before the figures are approved (run status up to awaiting_approval); from approved on, and for decided cases, the call is rejected. The internal processing note is never touched.",
"inputSchema": {
"type": "object",
"required": [
"case_id",
"note"
],
"properties": {
"note": {
"type": "string",
"description": "The explanation (1–8000 chars)"
},
"case_id": {
"type": "string",
"description": "UUID of the anomaly case"
},
"replace": {
"type": "boolean",
"description": "Required true to overwrite an existing note; without it the call is rejected and the existing text stays."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Vermerk an Auffälligkeit",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}Creates the first report draft of a run whose figures a person has already approved in the app (run status approved). Any other status is rejected with the status named; regenerating an existing report is not possible here (it can mark edited texts for review or drop them) and stays in the app. Fynsight's own AI writes the driver sentences of the headlines and the three summary sentences from the computed figures and the published explanations, so the figures and explanation texts of this period are sent to Fynsight's AI provider (see data flows in the documentation). The result is a DRAFT: it is reviewed, published and signed off in the app. If building the report fails, the run goes to failed (a new run and a new approval are then needed). Returns the deeplink to the report.
| Parameter | Type | Description |
|---|---|---|
| run_id * | string | UUID of the run (status approved) |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "generate-month-report",
"description": "Creates the first report draft of a run whose figures a person has already approved in the app (run status approved). Any other status is rejected with the status named; regenerating an existing report is not possible here (it can mark edited texts for review or drop them) and stays in the app. Fynsight's own AI writes the driver sentences of the headlines and the three summary sentences from the computed figures and the published explanations, so the figures and explanation texts of this period are sent to Fynsight's AI provider (see data flows in the documentation). The result is a DRAFT: it is reviewed, published and signed off in the app. If building the report fails, the run goes to failed (a new run and a new approval are then needed). Returns the deeplink to the report.",
"inputSchema": {
"type": "object",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "string",
"description": "UUID of the run (status approved)"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Berichtsentwurf erzeugen",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Creates an AI DRAFT explanation (status ai_draft) for a position of the month report. The draft has a short form (`summary`: one sentence saying why the number deviates, no figures) and an optional `detail` (may name single amounts from the material). The material is the position's figures plus the notes and clarification answers of the decided cases of the run that belong to it. Drafts are created only on request (here or by a click in the app), never automatically; list-comment-status shows which positions are still open. A draft is never published automatically: a person reviews and publishes it in the app. The response returns `summary` and `detail`. An existing explanation is never overwritten silently (see replace_published).
| Parameter | Type | Description |
|---|---|---|
| run_id * | string | UUID of the run |
| target_key * | string | Position key: P&L label (tenant category), metric key (e.g. "ebitda"), cost center number, or "total". |
| target_type * | string | Position type |
| instructions | string | Optional hints for the draft |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
| replace_published | boolean | Required true to replace a comment that is already published (approved in the app); without it the call is rejected with COMMENT_PUBLISHED and the published text stays. |
List every organisation the authenticated user is a member of. Each entry reports the user's role, whether the org is a holding (is_holding, derived from its holding entitlement), and which org is currently active for this MCP session (is_active=true). parent_organization_id holds the parent organisation's ID for a child organisation, and null otherwise; parent_relation says what kind of child it is: 'client' (client tenant of a service provider) or 'subsidiary' (subsidiary of a holding), null for an organisation without a parent.
No parameters.
{
"name": "list_organizations",
"description": "List every organisation the authenticated user is a member of. Each entry reports the user's role, whether the org is a holding (is_holding, derived from its holding entitlement), and which org is currently active for this MCP session (is_active=true). parent_organization_id holds the parent organisation's ID for a child organisation, and null otherwise; parent_relation says what kind of child it is: 'client' (client tenant of a service provider) or 'subsidiary' (subsidiary of a holding), null for an organisation without a parent.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Organisationen auflisten",
"readOnlyHint": true,
"openWorldHint": false
}
}Switch the active organisation for subsequent MCP tool calls (e.g. get_periodic_summaries, query_kpis). The user must be a member and the target org must have an active subscription. The switch applies to this MCP client only, for every agent that uses it. Agents that work in parallel should not switch; they pass organization_id with each tool call instead, which runs that single call in the named organisation and leaves the active one unchanged.
| Parameter | Type | Description |
|---|---|---|
| organization_id * | number | Tenant ID to switch to. Must appear in list_organizations. |
{
"name": "switch_organization",
"description": "Switch the active organisation for subsequent MCP tool calls (e.g. get_periodic_summaries, query_kpis). The user must be a member and the target org must have an active subscription. The switch applies to this MCP client only, for every agent that uses it. Agents that work in parallel should not switch; they pass organization_id with each tool call instead, which runs that single call in the named organisation and leaves the active one unchanged.",
"inputSchema": {
"type": "object",
"required": [
"organization_id"
],
"properties": {
"organization_id": {
"type": "number",
"description": "Tenant ID to switch to. Must appear in list_organizations."
}
}
},
"annotations": {
"title": "Organisation wechseln",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
| Account categories, as in the category field of get_all_accounts. |
| operations | array | Metrics to compute (default: ['sum']) |
| text_query | string | Case-insensitive text filter on the booking text and reference, e.g. a customer or vendor name. |
| after_group | number | Pagination cursor: pagination.next_cursor of the previous call returns the next page of groups. |
| granularity | string | Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself. |
| cost_centers | array | Cost center numbers; get_cost_center_list maps names to numbers. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
| share_denominator | object | Denominator of 'share': bookings of one category and/or of the given accounts. Default: the total of all included data. |
{
"name": "compute_aggregates",
"description": "Aggregates bookings and account balances (sum, avg, mom, yoy, cumulative, share, count) by period, cost center, account or category. Amounts are ledger amounts (sign_convention \"ledger\", see sign_convention_note): revenue and expense are both positive as booked, a negative value reduces the account. Sums are therefore not result figures; get_periodic_summaries and aggregate_pnl_by_cost_center return the result effect (revenue +, expense −). A group that contains revenue and expense accounts has mixes_revenue_and_expense=true, and the response adds a warning. With group_by=account every sub-account is its own group; the group key carries account, sub_account (null = none) and account_ref. totals.sum covers all periods in scope regardless of granularity. mom/yoy compare with the previous bucket inside the requested window; the calendar previous month comes from get_periodic_summaries with include_previous. Groups are paged via after_group and pagination.next_cursor. available_range gives the tenant's full data range; an empty page does not mean there is no data. scope.pnl_reconciled=true means each month was cross-checked against the P&L; a warning then names period, both amounts and the difference. With text_query, cost_centers or categories the result is a subset by design and not reconciled. With text_query, scope.text_match gives matched_sum, unfiltered_sum (same accounts, cost centers and months without the search term) and matched_share_pct.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"periods": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[0-9]{4}(-(0[1-9]|1[0-2]|Q[1-4]))?$"
},
"description": "Months as YYYY-MM. The shorthands 'YYYY' and 'YYYY-Qn' (e.g. '2023', '2023-Q2') expand to exactly the months the tenant has data for. Omit for every available period."
},
"accounts": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[0-9]{1,7}(/[0-9]{1,5})?$"
},
"description": "Accounts as \"8400\" (main account, same as \"8400/000\") or \"8400/130\" (sub-account). Each entry matches exactly that variant (\"8400\" excludes \"8400/130\"); unknown accounts are rejected. This is the account_ref notation of get_all_accounts and of the compute_aggregates groups."
},
"group_by": {
"type": "array",
"items": {
"enum": [
"period",
"cost_center",
"account",
"category"
],
"type": "string"
},
"description": "Grouping dimensions"
},
"categories": {
"type": "array",
"items": {
"type": "string"
},
"description": "Account categories, as in the category field of get_all_accounts."
},
"operations": {
"type": "array",
"items": {
"enum": [
"sum",
"avg",
"mom",
"yoy",
"cumulative",
"share",
"count"
],
"type": "string"
},
"description": "Metrics to compute (default: ['sum'])"
},
"text_query": {
"type": "string",
"description": "Case-insensitive text filter on the booking text and reference, e.g. a customer or vendor name."
},
"after_group": {
"type": "number",
"description": "Pagination cursor: pagination.next_cursor of the previous call returns the next page of groups."
},
"granularity": {
"enum": [
"month",
"quarter",
"year",
"total"
],
"type": "string",
"description": "Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself."
},
"cost_centers": {
"type": "array",
"items": {
"type": "number"
},
"description": "Cost center numbers; get_cost_center_list maps names to numbers."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
},
"share_denominator": {
"type": "object",
"properties": {
"accounts": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[0-9]{1,7}(/[0-9]{1,5})?$"
},
"description": "Denominator accounts, \"8400\" or \"8400/130\"; exact variants like the accounts filter."
},
"category": {
"type": "string",
"description": "Category name whose total is the denominator."
}
},
"description": "Denominator of 'share': bookings of one category and/or of the given accounts. Default: the total of all included data."
}
}
},
"annotations": {
"title": "Summen und Auswertungen berechnen",
"readOnlyHint": true,
"openWorldHint": false
}
}| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
| include_previous | boolean | Attach previous_period/previous_comparison/delta_category_totals to each summary, comparing it against the calendar predecessor (default false). |
| include_account_totals | boolean | Attach `totals` (one row per account/sub-account with period_balance and account_ref) to every summary (default false: omitted, answer stays small). |
{
"name": "get_periodic_summaries",
"description": "P&L summaries per period: metrics (EBIT, EBITDA, margins, depreciation, financial, tax) and category_totals, as result effect (revenue +, expense −). Each summary's metrics.category_totals_sort_order gives the GuV-Explorer display order per category (lower sorts first). granularity quarter, year or total sums the months in the tool and re-derives the metrics. Per-account balances are omitted by default; include_account_totals=true adds `totals` per summary. include_previous compares each summary with its CALENDAR predecessor (loaded automatically; granularity total has none): previous_period, previous_comparison (per headline figure: current, previous, delta_absolute, delta_percentage) and delta_category_totals (same keys as category_totals, with label_ids, current, previous and the deltas). A category without bookings in a period that has computed metrics counts as 0, not null; delta_percentage is null when the previous value is 0. All deltas are null (not 0) when a side has no computed metrics. For quarter/year, if the bucket or its predecessor covers fewer months than the bucket length (3/12; see months_covered and previous_months_covered), all deltas are null and a warning names the period. Every response carries available_range ({from, to}, YYYY-MM); requested months without a ledger row are listed in missing_periods and named in a warning. An invalid period such as 2026-13 is rejected.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"date_to": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "End of a date range (YYYY-MM-DD or YYYY-MM), additive to `periods`. Independent of date_from — given alone, the range starts at the tenant's first available period. Omit both for all data."
},
"periods": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])$"
},
"description": "Months as YYYY-MM"
},
"date_from": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Start of a date range (YYYY-MM-DD or YYYY-MM), additive to `periods`. Independent of date_to — given alone, the range runs through the tenant's last available period. Omit both for all data."
},
"granularity": {
"enum": [
"month",
"quarter",
"year",
"total"
],
"type": "string",
"description": "Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
},
"include_previous": {
"type": "boolean",
"description": "Attach previous_period/previous_comparison/delta_category_totals to each summary, comparing it against the calendar predecessor (default false)."
},
"include_account_totals": {
"type": "boolean",
"description": "Attach `totals` (one row per account/sub-account with period_balance and account_ref) to every summary (default false: omitted, answer stays small)."
}
}
},
"annotations": {
"title": "GuV-Perioden abfragen",
"readOnlyHint": true,
"openWorldHint": false
}
}| date_from | string | Day-exact lower bound on transaction_date, inclusive (YYYY-MM-DD). Omit for no lower bound. |
| text_query | string | Literal case-insensitive substring of description OR reference; %, _ and \ are characters, not wildcards. |
| limit_count | number | Max rows: a whole number >= 1 (default: 200; values above 1000 are capped at 1000) |
| cost_centers | array | Cost center numbers; get_cost_center_list maps names to numbers. |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "search_cost_center_transactions",
"description": "Searches individual bookings. Each row has period, cost_center, account, sub_account, contra_account, contra_sub_account (null if none), amount, description, transaction_date (day-exact booking date), `id` (the transaction_id for propose-transaction-correction) and `source` (\"upload\" or \"manual\"), plus correction_status (\"none\" | \"pending\" | \"corrected\") and correction_role (null | \"reversal\" | \"rebooking\"): whether a booking has an open or approved correction, or is itself the reversal/re-booking line of one. accounts takes \"8400\" (main account) or \"8400/130\"; each entry matches exactly that variant and unknown accounts are rejected. text_query is a case-insensitive substring of description OR reference; % and _ are searched as characters, not as wildcards. limit_count is a whole number of at least 1 (default 200, values above 1000 are capped at 1000; anything else is rejected). With truncated=true more bookings match than were returned; beyond 1000 only narrowing the filters helps. available_range gives the tenant's data range. With group_by the response carries `groups` (by period and/or cost center, each with transaction_count and transactions_truncated) instead of `rows`. Counts are reported in total_count (returned bookings), group_count (groups) and transaction_count per group; limit_count is a cap, not a count. The tool returns single bookings; sums per month, cost center or account come from compute_aggregates.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"date_to": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01])$",
"description": "Day-exact upper bound on transaction_date, inclusive (YYYY-MM-DD). Omit for no upper bound."
},
"periods": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])$"
},
"description": "Months as YYYY-MM. Omit for every available period."
},
"accounts": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[0-9]{1,7}(/[0-9]{1,5})?$"
},
"description": "Accounts as \"8400\" (main account, same as \"8400/000\") or \"8400/130\" (sub-account). Each entry matches exactly that variant (\"8400\" excludes \"8400/130\"); unknown accounts are rejected. This is the account_ref notation of get_all_accounts and of the compute_aggregates groups."
},
"group_by": {
"type": "array",
"items": {
"enum": [
"period",
"cost_center"
],
"type": "string"
},
"description": "Optional. Groups the bookings by these fields; the response then carries `groups` instead of `rows`."
},
"date_from": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01])$",
"description": "Day-exact lower bound on transaction_date, inclusive (YYYY-MM-DD). Omit for no lower bound."
},
"text_query": {
"type": "string",
"description": "Literal case-insensitive substring of description OR reference; %, _ and \\ are characters, not wildcards."
},
"limit_count": {
"type": "number",
"description": "Max rows: a whole number >= 1 (default: 200; values above 1000 are capped at 1000)"
},
"cost_centers": {
"type": "array",
"items": {
"type": "number"
},
"description": "Cost center numbers; get_cost_center_list maps names to numbers."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Kostenstellen-Buchungen suchen",
"readOnlyHint": true,
"openWorldHint": false
}
}| after_cost_center | number | Pagination cursor: pagination.next_cursor of the previous call returns the next page |
| include_categories | boolean | Default false. true adds category_totals (label name → value, revenue +, expense −), category_label_ids (name → ids of the labels summed into it) and category_totals_sort_order to each row; fewer cost centers fit on a page. |
{
"name": "aggregate_pnl_by_cost_center",
"description": "P&L metrics per cost center and period across the full history, paginated over cost_center via after_cost_center and pagination.next_cursor (with categories each row counts several times against the page budget; the response states the weight). Amounts are result effect (revenue +, expense −). `revenue` is the sum of all labels in the tenant's revenue group; sales deductions and penalties booked on revenue-group labels are already netted in. include_categories=true adds the split per label (category_totals), and revenue is then the sum of the revenue-group categories. granularity quarter, year or total returns the finished rolled-up figures. available_range gives the overall time range. Hidden cost centers stay included and are marked as hidden on each row. Every number in cost_centers must be a known cost center (unknown numbers are rejected); a known cost center without P&L bookings in the range is listed in `warnings`. period_from/period_to must be valid (YYYY-MM or YYYY-MM-DD) and period_from must not be after period_to.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"metrics": {
"type": "array",
"items": {
"enum": [
"revenue",
"gross_margin",
"ebitda",
"ebit",
"ebt",
"net_income"
],
"type": "string"
},
"description": "Which metrics to return (default: all six)"
},
"period_to": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "End period YYYY-MM or YYYY-MM-DD (optional)"
},
"granularity": {
"enum": [
"month",
"quarter",
"year",
"total"
],
"type": "string",
"description": "Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself."
},
"period_from": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Start period YYYY-MM or YYYY-MM-DD (optional)"
},
"cost_centers": {
"type": "array",
"items": {
"type": "number"
},
"description": "Optional cost center numbers; get_cost_center_list maps names to numbers."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
},
"after_cost_center": {
"type": "number",
"description": "Pagination cursor: pagination.next_cursor of the previous call returns the next page"
},
"include_categories": {
"type": "boolean",
"description": "Default false. true adds category_totals (label name → value, revenue +, expense −), category_label_ids (name → ids of the labels summed into it) and category_totals_sort_order to each row; fewer cost centers fit on a page."
}
}
},
"annotations": {
"title": "GuV-Kennzahlen je Kostenstelle",
"readOnlyHint": true,
"openWorldHint": false
}
}| number |
| Optional cost center filter. |
| granularity | string | Breakdown level (default: category) |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "get_budget_vs_actual",
"description": "Budget (Soll) vs. actual (Ist) with variance and YTD summary for one plan (plan_id from list_budget_plans). detail=summary omits period_rows and row_count. Besides the per-category rows (period_rows, ytd_summary) the response carries derived P&L metrics for plan and actual: `metrics` (per period) and `metrics_ytd` (all periods of the response) with revenue, other_income, cogs, opex, depreciation, financial, tax, gross_margin, ebitda, ebit, ebt and net_income (= Jahresueberschuss), each with budget, actual, variance and variance_pct. They are computed from tenant_config.pnl_labels exactly like get_periodic_summaries.metrics. `unmapped_categories` lists categories with amounts but no subtotal_group (not part of any metric). With cost_center set, actuals of the metrics are tenant-wide (see metrics_note). Account level (granularity=account): one row per account/sub-account of the plan, key \"8400\" (the main account = sub-account 000, compared against the actuals of the main account only) or \"8400/130\" (a specific sub-account, compared against that sub-account only); the two never overlap and are not summed. All granularities (category, account and BAB row) use the result view: revenue positive, expense negative, plan and actual alike (budget plans stored with positive expenses are normalized), so the account rows of a category add up to that category's value and a positive variance always means better for the result.",
"inputSchema": {
"type": "object",
"required": [
"plan_id"
],
"properties": {
"detail": {
"enum": [
"summary",
"rows"
],
"type": "string",
"description": "rows (default): full period_rows + row_count; summary: only ytd_summary, metrics, metrics_ytd and unmapped_categories."
},
"date_to": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "End date YYYY-MM-DD or YYYY-MM. Omit for full plan range."
},
"plan_id": {
"type": "string",
"description": "UUID of the budget plan (the id from list_budget_plans)"
},
"date_from": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Start date YYYY-MM-DD or YYYY-MM. Omit for full plan range."
},
"cost_center": {
"type": "number",
"description": "Optional cost center filter."
},
"granularity": {
"enum": [
"category",
"account",
"knw_row"
],
"type": "string",
"description": "Breakdown level (default: category)"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Budget vs. Ist",
"readOnlyHint": true,
"openWorldHint": false
}
}{
"name": "get_metric_trend",
"description": "Time series of a single named metric across periods, with month-over-month and year-over-year change per point (value, change, change_percentage, yoy_change, yoy_change_percentage, compared_period). The metric is one bucket (revenue, other_income, cogs, opex, depreciation, financial, tax), one derived P&L aggregate (gross_margin, ebitda, ebit, ebt, net_income) or one P&L category from tenant_config.pnl_labels. get_periodic_summaries returns all metrics of a period at once (including sort_order and include_previous); compute_aggregates covers account/cost-center/category sums with grouping, share or cumulative but cannot compute the derived aggregates (ebitda etc.). Time range: `periods` (a count of the most recent periods, default 12) or `date_from`/`date_to`; not a period list as in other tools.",
"inputSchema": {
"type": "object",
"required": [
"metric"
],
"properties": {
"metric": {
"type": "string",
"description": "Metric name: one of \"revenue\", \"other_income\", \"cogs\", \"opex\", \"depreciation\", \"financial\", \"tax\" (buckets) or \"gross_margin\", \"ebitda\", \"ebit\", \"ebt\", \"net_income\" (aggregates), or any P&L category name from tenant_config.pnl_labels."
},
"date_to": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Alternative to `periods`: end of a date range (YYYY-MM-DD or YYYY-MM), independent of date_from."
},
"periods": {
"type": "number",
"description": "Number of most recent periods to include (default 12). A count, not a period list."
},
"date_from": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Alternative to `periods`: start of a date range (YYYY-MM-DD or YYYY-MM), independent of date_to."
},
"granularity": {
"enum": [
"month",
"quarter",
"year",
"total"
],
"type": "string",
"description": "Time bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. The tool rolls the months up itself."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Kennzahlen-Trend",
"readOnlyHint": true,
"openWorldHint": false
}
}| number |
| ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "export-report",
"description": "Generates a structured financial report as JSON. Pass either period (one month) or date_from/date_to (a range), never both; invalid or contradictory values are rejected with an error. report_type=pnl: the P&L lines of the period or range as one list ordered by period, without a period argument ALL months (a long history can be large). report_type=category-breakdown: summary figures and category totals. Default is the latest month with data and the output carries one month. For a range of several months it returns months[] (one entry per month, each with summary, categories and category_totals) plus total (the sum of the months with summary re-derived from the summed buckets, not added up from the monthly summaries). report_type=kpi-dashboard: the KPI values with change against the previous month. Default is the latest month with data; for a range of several months it returns months[] with the KPIs of each month, at most 12 months per call (more is rejected). category-breakdown and kpi-dashboard answer with an error naming the available data range when the period or range has no data; in a multi-month range, months without data are listed in missing_periods.",
"inputSchema": {
"type": "object",
"required": [
"report_type"
],
"properties": {
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])$",
"description": "One month (YYYY-MM). Use either period or date_from/date_to, not both. Without any time argument: pnl returns all months, category-breakdown and kpi-dashboard the latest month with data."
},
"date_to": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "End of a range (YYYY-MM-DD or YYYY-MM). Optional on its own: the range then ends at the last month with data. Not allowed together with period; must not be before date_from."
},
"date_from": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Start of a range (YYYY-MM-DD or YYYY-MM). Optional on its own: the range then starts at the first month with data. Not allowed together with period."
},
"report_type": {
"enum": [
"pnl",
"kpi-dashboard",
"category-breakdown"
],
"type": "string",
"description": "Type of report to generate"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Bericht exportieren",
"readOnlyHint": true,
"openWorldHint": false
}
}{
"name": "upload-budget-entries",
"description": "Inserts or updates budget entries (monthly values) of a plan; a value that already exists for the same entry and month is overwritten. Exactly one of category, account or knw_row_number is set per entry. An account entry may name one sub-account as part of the account, e.g. \"8400/130\" (slash, as shown in the app); there is no separate sub_account parameter. The main account is sub-account 000: \"8400\" and \"8400/000\" mean the same and are compared against the actuals of the main account ONLY (not the sum of the sub-accounts; main-account and sub-account entries never overlap). If the account has no main account but exactly ONE sub-account, that one is used; with SEVERAL the entry is rejected (BUDGET_ACCOUNT_AMBIGUOUS, sub-accounts listed). A sub-account that does not exist for the tenant is rejected (BUDGET_ACCOUNT_UNKNOWN). An account unknown to the tenant is still accepted. Amounts are signed (expenses negative); plans created from a file upload that store expenses as positive magnitudes are rejected. For a forecast plan (type=forecast) the entries cover the ACTUAL values of the closed months plus the forecast of the remaining months (see create-budget-plan); without the closed months the year/YTD comparison is wrong. A category name that matches no P&L label is rejected with the list of valid category names and nothing is written.",
"inputSchema": {
"type": "object",
"required": [
"plan_id",
"entries"
],
"properties": {
"entries": {
"type": "array",
"items": {
"type": "object",
"required": [
"period",
"amount"
],
"properties": {
"amount": {
"type": "number",
"description": "Budget amount (negative for expenses)"
},
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Month as YYYY-MM or YYYY-MM-DD (e.g. \"2025-01\"); stored as the first of the month"
},
"account": {
"type": [
"number",
"string"
],
"description": "DATEV account as shown in the app: 4400 or \"4400\" (main account) or \"8400/130\" (account/sub-account, slash); \"8400/000\" = \"8400\""
},
"category": {
"type": "string",
"description": "P&L category name (e.g. \"Umsatzerlöse\")"
},
"cost_center": {
"type": "number",
"description": "Optional cost center number the entry belongs to"
},
"knw_row_number": {
"type": "number",
"description": "BAB row number from KNW cost report (e.g. 2190)"
}
}
},
"description": "Budget entries to upsert"
},
"plan_id": {
"type": "string",
"description": "UUID of the target budget plan"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Budgetwerte hochladen",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "propose-manual-adjustment",
"description": "Proposes a manual correction booking (Korrekturbuchung) for a month, e.g. an unbooked invoice or an anomaly correction on a specific account and cost center. This does NOT post to the ledger: it creates a PENDING proposal that a human approves in the web app.",
"inputSchema": {
"type": "object",
"required": [
"account",
"cost_center",
"period",
"amount"
],
"properties": {
"note": {
"type": "string",
"description": "Optional internal note explaining the correction"
},
"amount": {
"type": "number",
"description": "Amount in the ledger sign convention: POSITIVE on an expense account books ADDITIONAL expense (an unbooked invoice is positive, never negative), POSITIVE on a revenue account books additional revenue. Use a NEGATIVE amount only to REDUCE a booked amount (e.g. moving cost off an account)."
},
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "Accounting month (YYYY-MM or YYYY-MM-DD)"
},
"account": {
"type": "string",
"description": "Account as shown in the app: \"4321\", or with sub-account \"8400/130\" (account/sub-account, slash). Without a sub-account the sub-account is resolved automatically when the account has exactly one variant; if there are several, the error lists the known variants. Must exist for the tenant."
},
"cost_center": {
"type": "number",
"description": "Cost center / Kostenstelle number (e.g. 93)"
},
"description": {
"type": "string",
"description": "Booking text, e.g. \"Gies Dienstleistung\""
},
"contra_account": {
"type": "string",
"description": "Optional contra account (Gegenkonto), same notation: \"1200\" or \"1200/000\". Any account the tenant knows: in its chart of accounts or already used as a contra account in its bookings (e.g. bank, personal or balance sheet accounts from a KNW import). A bare number resolves if the tenant knows exactly one variant."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Korrekturbuchung vorschlagen",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}| ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "propose-transaction-correction",
"description": "Proposes a correction to an EXISTING ledger booking: wrong cost center, wrong account, wrong amount or wrong month. This does NOT change the original booking and does NOT post to the ledger: it creates a PENDING proposal that a human approves in the web app. On approval a reversal of the original booking plus a corrected re-booking are written. The transaction id is the `id` of a row from `search_cost_center_transactions`. A booking that does not exist yet is proposed with `propose-manual-adjustment`.",
"inputSchema": {
"type": "object",
"required": [
"transaction_id",
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "Why the booking is corrected; mandatory for the audit trail"
},
"new_amount": {
"type": "number",
"description": "New amount, in the same sign convention as the original booking (positive = expense/revenue on that account) — only if the amount changes; 0 means the booking was a duplicate and is only reversed"
},
"new_period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "New accounting month (YYYY-MM or YYYY-MM-DD) — only if the month changes"
},
"new_account": {
"type": "string",
"description": "New account — only if the account or its sub-account changes. Notation \"4321\" or \"8400/130\". Without a sub-account it is resolved automatically when the account has exactly one variant (the old sub-account is never carried over); if there are several, pass the full account/sub-account."
},
"transaction_id": {
"type": "string",
"description": "UUID of the existing booking, from `search_cost_center_transactions`"
},
"new_cost_center": {
"type": "number",
"description": "New cost center / Kostenstelle — only if the cost center changes"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Buchungskorrektur vorschlagen",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}{
"name": "update-manual-adjustment",
"description": "Edits a PENDING manual correction proposal (amount, account, cost center, description, note, period). Approved bookings cannot be edited; they are deleted in the app.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "UUID of the pending proposal"
},
"note": {
"type": "string",
"description": "New note"
},
"amount": {
"type": "number",
"description": "New amount, in the ledger sign convention: POSITIVE on an expense account books additional expense, POSITIVE on a revenue account books additional revenue. Use a NEGATIVE amount only to REDUCE a booked amount."
},
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01]))?$",
"description": "New month (YYYY-MM or YYYY-MM-DD)"
},
"account": {
"type": "string",
"description": "New account, \"4321\" or \"8400/130\". Without a sub-account it is resolved automatically when the account has exactly one variant; otherwise pass the full account/sub-account."
},
"cost_center": {
"type": "number",
"description": "New cost center"
},
"description": {
"type": "string",
"description": "New booking text"
},
"contra_account": {
"type": "string",
"description": "New contra account, same notation and rules as in propose-manual-adjustment."
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Korrekturvorschlag bearbeiten",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}| status | string | open (default): unresolved cases; decided: resolved + dismissed; all: both |
| after_id | string | view cases: cursor, the next_cursor of the previous page |
| category | string | Filter by P&L category, name as shown in the app. An ambiguous name is rejected; pnl_label_id then identifies the category. |
| severity | string | Filter by severity |
| cost_center | number | Filter by cost center |
| pnl_label_id | string | Filter by P&L category id (UUID); use when the category name is ambiguous |
| min_abs_delta | number | Only cases with abs(delta) at least this amount (cases without delta are excluded) |
| organization_id | number | ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization. |
{
"name": "list-open-anomaly-cases",
"description": "Lists the anomaly cases of a Monatsreporting run: view summary (default) gives counts, sums and top cases, view cases lists single cases, filtered and paginated. status: open (default), decided (resolved/dismissed) or all. by_cost_center entries carry hidden (hidden in the app) and are never dropped. Amounts (actual, reference, delta = actual - reference, delta_pct) are taken unchanged from the detection rules; only budget_deviation and mom_outlier carry delta (sign_flip: actual = current, duplicate_suspicion: actual = amount, missing_account: no amount). sum_abs_delta is per kind, never mixed across kinds (null plus cases_without_delta for kinds without delta). commentary is the case note (Reporting-Vermerk): material for the comment of the position while the case is open, the short form of that comment once a person accepts it in the app. The report shows comments (list-comment-status), not case notes. commentary_source: ai = AI review, user = a person, null = older case. A follow_up case checks an earlier watch item: watch holds the original statement and the result (recurred true/false/null; position_missing true = position not assessable this month, which is not \"did not recur\"). Each case carries clarification (open or answered question with context, suggestions, answer) or null; the summary counts open_clarifications and follow_ups. updated_at is the last change of the case, not the decision time.",
"inputSchema": {
"type": "object",
"required": [
"run_id"
],
"properties": {
"top": {
"type": "number",
"description": "view summary: number of top cases (default 20, max 50)"
},
"kind": {
"enum": [
"budget_deviation",
"mom_outlier",
"missing_account",
"sign_flip",
"duplicate_suspicion",
"other",
"follow_up"
],
"type": "string",
"description": "Filter by case kind"
},
"view": {
"enum": [
"summary",
"cases"
],
"type": "string",
"description": "summary (default): counts, sums and top cases; cases: single cases, paginated"
},
"limit": {
"type": "number",
"description": "view cases: page size (default 50, silently capped at 200)"
},
"run_id": {
"type": "string",
"description": "UUID of the run"
},
"status": {
"enum": [
"open",
"decided",
"all"
],
"type": "string",
"description": "open (default): unresolved cases; decided: resolved + dismissed; all: both"
},
"after_id": {
"type": "string",
"description": "view cases: cursor, the next_cursor of the previous page"
},
"category": {
"type": "string",
"description": "Filter by P&L category, name as shown in the app. An ambiguous name is rejected; pnl_label_id then identifies the category."
},
"severity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string",
"description": "Filter by severity"
},
"cost_center": {
"type": "number",
"description": "Filter by cost center"
},
"pnl_label_id": {
"type": "string",
"description": "Filter by P&L category id (UUID); use when the category name is ambiguous"
},
"min_abs_delta": {
"type": "number",
"description": "Only cases with abs(delta) at least this amount (cases without delta are excluded)"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
}
}
},
"annotations": {
"title": "Offene Auffälligkeiten",
"readOnlyHint": true,
"openWorldHint": false
}
}{
"name": "get-variance-bridge",
"description": "Result bridge for a month: EBITDA, EBIT and net income from a comparison value to actual, step by step per P&L category. READ ONLY. compare_to: previous_month, previous_quarter_month, previous_year or budget (plan_id optional, only with budget; default is the active plan of the year of the period, without one the call fails with NO_ACTIVE_BUDGET_PLAN). All amounts are result impact (revenue +, expense -, positive = improves the result; deltas = actual - comparison). start/end come from the computed metrics, the steps from category deltas, check.reconciles proves they add up (on unrounded values). unassigned = result change no category of this metric explains (labels without id or subtotal group, accounts without label); excluded lists what is left out (unlabeled_accounts, labels_without_group) and a warning appears when either is non-empty. rounding_difference = end - (start + steps + other + unassigned) on the rounded figures. Steps carry sort_order (P&L order) and auffaellig; the list is sorted by absolute delta. Small steps (below other_threshold, share of the absolute total change, default 0.05) are collapsed into other with their list.",
"inputSchema": {
"type": "object",
"required": [
"period",
"compare_to"
],
"properties": {
"period": {
"type": "string",
"pattern": "^[0-9]{4}-(0[1-9]|1[0-2])$",
"description": "Month, YYYY-MM"
},
"plan_id": {
"type": "string",
"description": "UUID of the budget plan; only with compare_to budget. Omitted: active plan of the year"
},
"compare_to": {
"enum": [
"previous_month",
"previous_quarter_month",
"previous_year",
"budget"
],
"type": "string",
"description": "Comparison value"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
},
"other_threshold": {
"type": "number",
"description": "Share (0..0.5, default 0.05) of the absolute total change below which categories are collapsed into other"
}
}
},
"annotations": {
"title": "Ergebnisbrücke",
"readOnlyHint": true,
"openWorldHint": false
}
}{
"name": "draft-report-comment",
"description": "Creates an AI DRAFT explanation (status ai_draft) for a position of the month report. The draft has a short form (`summary`: one sentence saying why the number deviates, no figures) and an optional `detail` (may name single amounts from the material). The material is the position's figures plus the notes and clarification answers of the decided cases of the run that belong to it. Drafts are created only on request (here or by a click in the app), never automatically; list-comment-status shows which positions are still open. A draft is never published automatically: a person reviews and publishes it in the app. The response returns `summary` and `detail`. An existing explanation is never overwritten silently (see replace_published).",
"inputSchema": {
"type": "object",
"required": [
"run_id",
"target_type",
"target_key"
],
"properties": {
"run_id": {
"type": "string",
"description": "UUID of the run"
},
"target_key": {
"type": "string",
"description": "Position key: P&L label (tenant category), metric key (e.g. \"ebitda\"), cost center number, or \"total\"."
},
"target_type": {
"enum": [
"pnl_line",
"summary_metric",
"cost_center",
"total"
],
"type": "string",
"description": "Position type"
},
"instructions": {
"type": "string",
"description": "Optional hints for the draft"
},
"organization_id": {
"type": "number",
"description": "ID of the organization this call runs in (from list_organizations). Required for tools that change data when you belong to more than one organization. Read tools use the active organization when omitted. Does not change the active organization."
},
"replace_published": {
"type": "boolean",
"description": "Required true to replace a comment that is already published (approved in the app); without it the call is rejected with COMMENT_PUBLISHED and the published text stays."
}
}
},
"annotations": {
"title": "Kommentar-Entwurf erzeugen",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}