Atisbo is an MCP server published by io.github.brian8a1, hosted at app.atisbo.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 8 tools, including atisbo_orient, atisbo_lookup, atisbo_capture, atisbo_decide, atisbo_map.
MCP tools over one Atisbo workspace: Signals, Opportunities, Backlog, Decisions, Living Documents.
11 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Workspace orientation. Modes: snapshot, whats_new, strategy, integrations. Continue the user's existing workflow; never create a parallel backlog. Living docs cite snippet:// refs — open atisbo_lookup mode=open; corpus via claim depth=work; aggregates via atisbo_analyze; edit via atisbo_lookup mode=doc_patch_context then atisbo_capture mode=patch_artefact (living documents; manual Knowledge documents are edited in place with atisbo_capture mode=update_artefact).
| Parameter | Type | Description |
|---|---|---|
| mode | string | snapshot (alias: workspace)=task; whats_new=since_checkpoint; strategy/integrations none. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest. |
| task | string | triage=untriaged inbox; planning=confirmed opportunities by priority; operations=signals & integrations; executive=KPIs & strategy. |
| depth | string |
None yet. Changes appear after a server's second daily check.
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.
| summary=compact; work=full (default). |
| limit | number | Max items. snapshot clamps to 20; whats_new to 50. |
| cursor | string | Pagination cursor. |
| since_checkpoint | string | ISO 8601 checkpoint for delta reads. |
{
"name": "atisbo_orient",
"title": "Orient: workspace snapshot and workflow state",
"description": "Workspace orientation. Modes: snapshot, whats_new, strategy, integrations. Continue the user's existing workflow; never create a parallel backlog. Living docs cite snippet:// refs — open atisbo_lookup mode=open; corpus via claim depth=work; aggregates via atisbo_analyze; edit via atisbo_lookup mode=doc_patch_context then atisbo_capture mode=patch_artefact (living documents; manual Knowledge documents are edited in place with atisbo_capture mode=update_artefact).",
"inputSchema": {
"type": "object",
"properties": {
"mode": {
"type": "string",
"description": "snapshot (alias: workspace)=task; whats_new=since_checkpoint; strategy/integrations none. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest."
},
"task": {
"enum": [
"triage",
"planning",
"operations",
"executive"
],
"type": "string",
"description": "triage=untriaged inbox; planning=confirmed opportunities by priority; operations=signals & integrations; executive=KPIs & strategy."
},
"depth": {
"enum": [
"summary",
"work",
"brief"
],
"type": "string",
"description": "summary=compact; work=full (default)."
},
"limit": {
"type": "number",
"minimum": 1,
"description": "Max items. snapshot clamps to 20; whats_new to 50."
},
"cursor": {
"type": "string",
"description": "Pagination cursor."
},
"since_checkpoint": {
"type": "string",
"description": "ISO 8601 checkpoint for delta reads."
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {}
}
},
"annotations": {
"category": "query",
"readOnlyHint": true,
"strict_output": false,
"destructiveHint": false,
"supports_cursor": true,
"supports_idempotency": false,
"requires_confirmation": false,
"supports_since_checkpoint": true
}
}Find or open Atisbo entities: snippets, queues, outcomes and implementation context across modes.
| Parameter | Type | Description |
|---|---|---|
| ref | string | open: ref (claim:UUID, snippet://UUID) or bare SEN-n (→ solution:<uuid>). |
| sha | string | deployment: SHA to check. |
| mode * | string | Notes per mode in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest. |
| refs | array | open: several refs (max 10; SEN-n accepted). |
| type | string | claims: classification. |
| view | string | work_queue: ONE bucket, complete. |
| depth | string | summary=compact; work=full; evidence (claims)=evidence+decisions, no score internals. |
| focus | string | claims: agent_work | all. |
| limit | number | Max results (1–200); page with next_cursor. |
| query | string | Topic search: claims/solutions/knowledge/context; resolve: name→id. |
| scope | string | Scope for context / living_doc list. |
| state | string | work tokens (todo=DESIGNING); post-launch kinds. |
| types | array | resolve: entity kinds. |
| cursor | string | Cursor from a prior response. |
| entity | string | get: which kind the id field names. |
| map_id | any | Map id: UUID or short ref (8+ hex, map:hex, SEN-n) — resolved first. |
| status | string | Status filter. |
| node_id | any | Node id: UUID or short ref (8+ hex, node:hex, SEN-n) — get, and claims/solutions filter. |
| sort_by | string | Solution order (evidence-weighted × boost). |
| anchored | string | Claim list anchoring filter. |
| category | string | knowledge: exact category filter. |
| claim_id | any | Claim UUID or short ref (8+ hex, claim:hex, SEN-n) — resolved first. |
| scope_id | string | Scope UUID (omit for company/workspace). |
| claim_ids | array | get: batch read, max 10 claim ids. |
| lifecycle | array | IDEA|DESIGNING|IN_DEVELOPMENT|IN_REVIEW|LAUNCHED|CANCELED; case and separators ignored. |
| target_id | any | Claim/solution/node/map id: UUID or short ref (8+ hex, hub:hex, SEN-n) — resolved first. |
| agent_name | string | solutions: rows HELD by this agent. |
| command_id | string | receipts: probe one write by a listed receipt key; omit = latest 25. |
| scope_type | string | Alias of scope; workspace=company. |
| claim_state | string | Claim state; open=untouched. |
| debug_score | boolean | get claim: PowerScore breakdown. |
| document_id | string | Living document UUID. |
| review_kind | string | unreviewed only — see atisbo_decide mark_reviewed. |
| solution_id | any | Solution UUID or short ref (8+ hex, solution:hex, SEN-n) — resolved first. |
| state_bucket | array | claims/signals: the row's own Opportunities bucket; needs_followup = Map's "Came back". Omit = all. |
| action_cursor | string | work_queue action_queue cursor; restart after mutations. |
| content_limit | number | |
| include_stale | boolean | claims: include stale claims. |
| content_offset | number | |
| dirty_event_id | string | doc_patch_context: loads this event's snippets. |
| evidence_limit | number | get claim: evidence page one (1–25); cursor for the rest. |
| triage_outcome | string | claims: triage verdict; review=pending; processing=in-flight. |
| exception_cursor | string | pages pm_exceptions. |
| judgement_cursor | string | pages needs_judgement. |
| min_attempt_number | number | |
| operational_block_cursor | string | work_queue: pages operational_blocks. |
{
"name": "atisbo_lookup",
"title": "Lookup: find and open Atisbo entities",
"description": "Find or open Atisbo entities: snippets, queues, outcomes and implementation context across modes.",
"inputSchema": {
"type": "object",
"required": [
"mode"
],
"properties": {
"ref": {
"type": "string",
"maxLength": 120,
"minLength": 3,
"description": "open: ref (claim:UUID, snippet://UUID) or bare SEN-n (→ solution:<uuid>)."
},
"sha": {
"type": "string",
"description": "deployment: SHA to check."
},
"mode": {
"type": "string",
"description": "Notes per mode in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest."
},
"refs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 120,
"minLength": 3
},
"maxItems": 10,
"description": "open: several refs (max 10; SEN-n accepted)."
},
"type": {
"enum": [
"problem",
"idea",
"question",
"unclassified"
],
"type": "string",
"description": "claims: classification."
},
"view": {
"enum": [
"executable",
"propose",
"needs_pm",
"awaiting_merge",
"premise_settled"
],
"type": "string",
"description": "work_queue: ONE bucket, complete."
},
"depth": {
"enum": [
"summary",
"work",
"evidence",
"brief"
],
"type": "string",
"description": "summary=compact; work=full; evidence (claims)=evidence+decisions, no score internals."
},
"focus": {
"enum": [
"agent_work",
"all"
],
"type": "string",
"description": "claims: agent_work | all."
},
"limit": {
"type": "number",
"maximum": 200,
"minimum": 1,
"description": "Max results (1–200); page with next_cursor."
},
"query": {
"type": "string",
"maxLength": 500,
"minLength": 2,
"description": "Topic search: claims/solutions/knowledge/context; resolve: name→id."
},
"scope": {
"enum": [
"company",
"node",
"claim",
"solution",
"map"
],
"type": "string",
"description": "Scope for context / living_doc list."
},
"state": {
"enum": [
"active",
"todo",
"draft",
"in_review",
"launched",
"proposed",
"monitoring",
"needs_review",
"came_back",
"didnt_work",
"partly_worked",
"worked",
"delivered",
"replaced",
"canceled"
],
"type": "string",
"description": "work tokens (todo=DESIGNING); post-launch kinds."
},
"types": {
"type": "array",
"items": {
"enum": [
"claim",
"solution",
"node",
"map"
],
"type": "string"
},
"maxItems": 4,
"description": "resolve: entity kinds."
},
"cursor": {
"type": "string",
"description": "Cursor from a prior response."
},
"entity": {
"enum": [
"claim",
"solution",
"node",
"map"
],
"type": "string",
"description": "get: which kind the id field names."
},
"map_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "string",
"maxLength": 80,
"minLength": 3
}
],
"description": "Map id: UUID or short ref (8+ hex, map:hex, SEN-n) — resolved first."
},
"status": {
"enum": [
"active",
"all",
"archived",
"noise"
],
"type": "string",
"description": "Status filter."
},
"node_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "string",
"maxLength": 80,
"minLength": 3
}
],
"description": "Node id: UUID or short ref (8+ hex, node:hex, SEN-n) — get, and claims/solutions filter."
},
"sort_by": {
"enum": [
"priority",
"created_at",
"lifecycle"
],
"type": "string",
"description": "Solution order (evidence-weighted × boost)."
},
"anchored": {
"enum": [
"any",
"anchored",
"unanchored"
],
"type": "string",
"description": "Claim list anchoring filter."
},
"category": {
"type": "string",
"maxLength": 60,
"description": "knowledge: exact category filter."
},
"claim_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "string",
"maxLength": 80,
"minLength": 3
}
],
"description": "Claim UUID or short ref (8+ hex, claim:hex, SEN-n) — resolved first."
},
"scope_id": {
"type": "string",
"format": "uuid",
"description": "Scope UUID (omit for company/workspace)."
},
"claim_ids": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80,
"minLength": 3
},
"maxItems": 10,
"description": "get: batch read, max 10 claim ids."
},
"lifecycle": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"description": "IDEA|DESIGNING|IN_DEVELOPMENT|IN_REVIEW|LAUNCHED|CANCELED; case and separators ignored."
},
"target_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "string",
"maxLength": 80,
"minLength": 3
}
],
"description": "Claim/solution/node/map id: UUID or short ref (8+ hex, hub:hex, SEN-n) — resolved first."
},
"agent_name": {
"type": "string",
"maxLength": 120,
"description": "solutions: rows HELD by this agent."
},
"command_id": {
"type": "string",
"maxLength": 200,
"description": "receipts: probe one write by a listed receipt key; omit = latest 25."
},
"scope_type": {
"enum": [
"company",
"workspace",
"node",
"claim",
"solution",
"map"
],
"type": "string",
"description": "Alias of scope; workspace=company."
},
"claim_state": {
"enum": [
"open",
"in_progress",
"resolved"
],
"type": "string",
"description": "Claim state; open=untouched."
},
"debug_score": {
"type": "boolean",
"description": "get claim: PowerScore breakdown."
},
"document_id": {
"type": "string",
"format": "uuid",
"description": "Living document UUID."
},
"review_kind": {
"enum": [
"signal_triage",
"claim_structure",
"solution_quality"
],
"type": "string",
"description": "unreviewed only — see atisbo_decide mark_reviewed."
},
"solution_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "string",
"maxLength": 80,
"minLength": 3
}
],
"description": "Solution UUID or short ref (8+ hex, solution:hex, SEN-n) — resolved first."
},
"state_bucket": {
"type": "array",
"items": {
"enum": [
"open",
"in_progress",
"monitoring",
"awaiting_review",
"needs_followup",
"resolved"
],
"type": "string"
},
"maxItems": 6,
"description": "claims/signals: the row's own Opportunities bucket; needs_followup = Map's \"Came back\". Omit = all."
},
"action_cursor": {
"type": "string",
"description": "work_queue action_queue cursor; restart after mutations."
},
"content_limit": {
"type": "number"
},
"include_stale": {
"type": "boolean",
"description": "claims: include stale claims."
},
"content_offset": {
"type": "number"
},
"dirty_event_id": {
"type": "string",
"format": "uuid",
"description": "doc_patch_context: loads this event's snippets."
},
"evidence_limit": {
"type": "number",
"maximum": 25,
"minimum": 1,
"description": "get claim: evidence page one (1–25); cursor for the rest."
},
"triage_outcome": {
"enum": [
"processing",
"review",
"signal",
"noise"
],
"type": "string",
"description": "claims: triage verdict; review=pending; processing=in-flight."
},
"exception_cursor": {
"type": "string",
"description": "pages pm_exceptions."
},
"judgement_cursor": {
"type": "string",
"description": "pages needs_judgement."
},
"min_attempt_number": {
"type": "number"
},
"operational_block_cursor": {
"type": "string",
"description": "work_queue: pages operational_blocks."
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {}
}
},
"annotations": {
"category": "query",
"readOnlyHint": true,
"strict_output": false,
"destructiveHint": false,
"supports_cursor": true,
"supports_idempotency": false,
"requires_confirmation": false,
"supports_since_checkpoint": false
}
}Capture Signals or knowledge; update, patch or add evidence to artefacts.
| Parameter | Type | Description |
|---|---|---|
| ops | any | |
| body | any | |
| mode * | string | Capture mode. Notes per mode in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest. |
| note | string | Why it matters. |
| text | string | Signal text. |
| items | array | Batch; max 100 items. |
| title | string | Knowledge title. |
| source | string | Signal source. |
| content | string | Knowledge content. |
| message | any | |
| node_id | string | knowledge: alias for scope_id. |
| patches | any | |
| category | string | knowledge: label hint. |
| claim_id | string | knowledge: alias for scope_id. |
| document | object | signal: backing doc → claim-scoped Knowledge. |
| evidence | object | Evidence fields; document_id top-level. |
| modality | string | Q=Quote, O=Observation, M=Metric; else inferred. |
| patchOps | any | |
| scope_id | any | Target scope UUID; required for node/claim/map. |
| file_name | string | |
| mime_type | string | |
| patch_ops | array | |
| agent_name | string | |
| scope_type | string | Scope kind; company = workspace. |
| attachments | array | 1-5 files; 3 MB combined. |
| document_id | string | Living document UUID. |
| solution_id | string | knowledge: alias for scope_id. |
| capture_mode | string | Knowledge routing. |
| captured_from | string | |
| change_summary | string | patch_artefact requires change_summary (or note): one sentence of what changed. |
| classification | string | Classification hint. |
| dirty_event_id | string | Dirty event |
| knowledge_kind | string | one of ["auto","transcript","transcript_customer","notes"] |
| coverage_updates | any | buckets snippets/ideas/claims; snippets[].{snippet_id,status,rationale} |
| client_request_id | string | signal: retry key. |
| proposed_solution | object | signal: draft Solution born linked on the claim. |
| on_behalf_of_person | boolean | |
| expected_content_hash | string | doc_patch_context content_hash |
| corrects_prior_evidence | boolean | signal: CORRECTS prior evidence — skips dedup. |
| expected_patch_lock_hash | string | doc_patch_context patch_lock_hash |
{
"name": "atisbo_capture",
"title": "Capture: record evidence and patches",
"description": "Capture Signals or knowledge; update, patch or add evidence to artefacts.",
"inputSchema": {
"type": "object",
"required": [
"mode"
],
"properties": {
"ops": {},
"body": {},
"mode": {
"type": "string",
"description": "Capture mode. Notes per mode in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest."
},
"note": {
"type": "string",
"maxLength": 500,
"description": "Why it matters."
},
"text": {
"type": "string",
"maxLength": 5000,
"minLength": 10,
"description": "Signal text."
},
"items": {
"type": "array",
"items": {
"type": "object",
"required": [
"text",
"client_request_id"
],
"properties": {
"text": {
"type": "string",
"maxLength": 5000,
"minLength": 10,
"description": "Signal text; max 5000 chars."
},
"source": {
"enum": [
"manual",
"github",
"webhook"
],
"type": "string"
},
"modality": {
"enum": [
"Q",
"O",
"M"
],
"type": "string"
},
"classification": {
"enum": [
"problem",
"idea",
"question"
],
"type": "string"
},
"client_request_id": {
"type": "string",
"maxLength": 200,
"minLength": 8,
"description": "Idempotency key."
},
"corrects_prior_evidence": {
"type": "boolean"
}
}
},
"maxItems": 100,
"description": "Batch; max 100 items."
},
"title": {
"type": "string",
"maxLength": 200,
"description": "Knowledge title."
},
"source": {
"enum": [
"manual",
"github",
"webhook"
],
"type": "string",
"description": "Signal source."
},
"content": {
"type": "string",
"maxLength": 100000,
"description": "Knowledge content."
},
"message": {},
"node_id": {
"type": "string",
"format": "uuid",
"description": "knowledge: alias for scope_id."
},
"patches": {},
"category": {
"type": "string",
"maxLength": 60,
"description": "knowledge: label hint."
},
"claim_id": {
"type": "string",
"format": "uuid",
"description": "knowledge: alias for scope_id."
},
"document": {
"type": "object",
"required": [
"content"
],
"properties": {
"content": {
"type": "string",
"maxLength": 20000,
"minLength": 10
},
"file_name": {
"type": "string",
"maxLength": 200
},
"mime_type": {
"enum": [
"text/html",
"text/markdown"
],
"type": "string"
}
},
"description": "signal: backing doc → claim-scoped Knowledge."
},
"evidence": {
"type": "object",
"properties": {
"title": {
"type": "string",
"maxLength": 200,
"description": "Evidence block title."
},
"status": {
"enum": [
"supported",
"contradicted",
"inconclusive",
"tracking_missing",
"informational"
],
"type": "string",
"description": "Relation to the hypothesis."
},
"provider": {
"type": "string",
"maxLength": 80,
"description": "Provider name, e.g. posthog, amplitude, custom_sql."
},
"warnings": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 20,
"description": "Provider warnings shown with the block."
},
"block_type": {
"enum": [
"query",
"metric",
"external_insight",
"chart_snapshot",
"link"
],
"type": "string",
"description": "Evidence block kind."
},
"confidence": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Confidence from 0 to 1."
},
"query_text": {
"type": "string",
"maxLength": 20000,
"description": "Query, event name, API request, or investigation prompt."
},
"external_url": {
"type": "string",
"maxLength": 2048,
"description": "External insight/dashboard/query URL, if available."
},
"interpretation": {
"type": "string",
"maxLength": 5000,
"description": "What this evidence means in the artefact context."
},
"query_language": {
"enum": [
"hogql",
"sql",
"api_request",
"natural_language",
"event"
],
"type": "string",
"description": "Language of query_text."
},
"refresh_policy": {
"enum": [
"manual",
"scheduled",
"none"
],
"type": "string",
"description": "Refresh cadence for the snapshot."
},
"result_snapshot": {
"type": "object",
"properties": {
"summary": {
"type": "string",
"maxLength": 5000,
"description": "Text summary of tabular or non-numeric provider output."
},
"event_name": {
"type": "string",
"maxLength": 500,
"description": "Provider event/metric name for refreshable metric blocks."
},
"data_points": {
"type": "array",
"items": {
"type": "object",
"required": [
"date",
"value"
],
"properties": {
"date": {
"type": "string",
"maxLength": 80
},
"value": {
"type": "number"
}
}
},
"maxItems": 365,
"description": "Optional compact time series snapshot."
},
"latest_date": {
"type": "string",
"maxLength": 80,
"description": "Date or timestamp for latest_value."
},
"latest_value": {
"type": "number",
"description": "Latest numeric value from the provider, when available."
},
"time_range_days": {
"type": "number",
"maximum": 365,
"minimum": 1,
"description": "Lookback window for refreshable metric blocks. Defaults to 30."
}
},
"description": "Result snapshot; event_name + time_range_days make it refreshable."
}
},
"description": "Evidence fields; document_id top-level."
},
"modality": {
"enum": [
"Q",
"O",
"M"
],
"type": "string",
"description": "Q=Quote, O=Observation, M=Metric; else inferred."
},
"patchOps": {},
"scope_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"enum": [
"auto"
],
"type": "string"
}
],
"description": "Target scope UUID; required for node/claim/map."
},
"file_name": {
"type": "string",
"maxLength": 200
},
"mime_type": {
"type": "string",
"maxLength": 120
},
"patch_ops": {
"type": "array",
"items": {
"type": "object",
"required": [
"op",
"section_id",
"markdown"
],
"properties": {
"op": {
"enum": [
"append_to_section",
"replace_section",
"annotate",
"add_section"
],
"type": "string"
},
"kind": {
"enum": [
"note",
"contradiction",
"update"
],
"type": "string"
},
"markdown": {
"type": "string",
"maxLength": 20000
},
"section_id": {
"type": "string",
"maxLength": 64
}
}
},
"maxItems": 20
},
"agent_name": {
"type": "string",
"maxLength": 120
},
"scope_type": {
"enum": [
"company",
"workspace",
"node",
"claim",
"solution",
"map"
],
"type": "string",
"description": "Scope kind; company = workspace."
},
"attachments": {
"type": "array",
"items": {
"type": "object",
"required": [
"data_base64",
"file_name",
"mime_type"
],
"properties": {
"file_name": {
"type": "string",
"maxLength": 200
},
"mime_type": {
"enum": [
"image/png",
"image/jpeg",
"image/webp",
"application/pdf"
],
"type": "string"
},
"data_base64": {
"type": "string",
"maxLength": 4200000,
"minLength": 4,
"description": "Base64."
}
},
"description": "PNG/JPG/WebP/PDF; no extraction."
},
"maxItems": 5,
"description": "1-5 files; 3 MB combined."
},
"document_id": {
"type": "string",
"format": "uuid",
"description": "Living document UUID."
},
"solution_id": {
"type": "string",
"format": "uuid",
"description": "knowledge: alias for scope_id."
},
"capture_mode": {
"enum": [
"context_only",
"signals_only",
"context_and_signals"
],
"type": "string",
"description": "Knowledge routing."
},
"captured_from": {
"type": "string",
"maxLength": 120
},
"change_summary": {
"type": "string",
"maxLength": 300,
"description": "patch_artefact requires change_summary (or note): one sentence of what changed."
},
"classification": {
"enum": [
"problem",
"idea",
"question"
],
"type": "string",
"description": "Classification hint."
},
"dirty_event_id": {
"type": "string",
"format": "uuid",
"description": "Dirty event"
},
"knowledge_kind": {
"enum": [
"auto",
"transcript",
"transcript_customer",
"notes"
],
"type": "string"
},
"coverage_updates": {
"description": "buckets snippets/ideas/claims; snippets[].{snippet_id,status,rationale}"
},
"client_request_id": {
"type": "string",
"maxLength": 200,
"minLength": 8,
"description": "signal: retry key."
},
"proposed_solution": {
"type": "object",
"required": [
"title"
],
"properties": {
"title": {
"type": "string",
"maxLength": 200
},
"description": {
"type": "string",
"maxLength": 2000
}
},
"description": "signal: draft Solution born linked on the claim."
},
"on_behalf_of_person": {
"type": "boolean"
},
"expected_content_hash": {
"type": "string",
"maxLength": 64,
"description": "doc_patch_context content_hash"
},
"corrects_prior_evidence": {
"type": "boolean",
"description": "signal: CORRECTS prior evidence — skips dedup."
},
"expected_patch_lock_hash": {
"type": "string",
"maxLength": 64,
"description": "doc_patch_context patch_lock_hash"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {}
}
},
"annotations": {
"category": "write",
"readOnlyHint": false,
"strict_output": false,
"destructiveHint": true,
"supports_cursor": false,
"supports_idempotency": true,
"requires_confirmation": false,
"supports_since_checkpoint": false
}
}CURATE: evidence review/grouping, deal-breakers. EXECUTE: create, update, dispatch or delete Solutions, record Outcomes. DOCUMENT/GOVERN: living docs, coverage, schedules, knowledge, strategy. log_decision is only for external decisions; mutations log themselves. Writes require UUIDs. mode=declare_pm_exception marks a CLAIM as needing a human decision.
| Parameter | Type | Description |
|---|---|---|
| id | string | delete_knowledge/set_knowledge_category doc id. |
| mode * | string | Resolve names to UUIDs before mutating; notes per mode in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest. |
| note | string | record_outcome note; triage/log_decision rationale. |
| spec | object | |
| brief | string | dispatch_solution: agent brief. |
| force | boolean | Confirms an irreversible write (reassign_snippet moves that empty a claim; combine_claims merges). Re-send the refused call unchanged plus force:true. |
| reach | any | record_reach: {affected_users, base_users, base_definition, scope, segment?, method, source?, confidence?, measured_at?, measured_by?}. |
| title | string | |
| effort | number | Size estimate, person-weeks (never affects order). |
| matrix | array | validate_delivery / deliver: one entry per criterion. |
| pr_url | string | |
| reason | string | Why: ≤500 chars — longer text is refused, state the decision not the history. |
| status | string | Target classification. |
| comment | string | update_solution/deliver/dispatch: thread report. |
| hold_op | string | take | renew (holder) | release (holder) | revoke (PM force) | assign (names who it is for, scope-gated) | unassign. |
| mission | string | update_strategy: informational only. |
| node_id | string | |
| outcome | string | record_outcome: launch impact. |
| roadmap | string | update_strategy: informational only. |
| verdict | string | triage closes; log_decision takes the judgement answer. |
| category | string | set_knowledge_category; update_solution refuses it. |
| claim_id | string | Claim UUID (atisbo_lookup mode=resolve) |
| decision | string | max 500 chars. |
| scope_op | string | agent_scope verb: register | unregister | list. |
| strategy | string | update_strategy: the only functional field. |
| unassign | boolean | |
| assign_to | string | claim_hold op=assign target: who the claim is for. |
| claim_ids | array | |
| for_agent | string | agent_scope: whose scope (register/unregister target, list filter). |
| kpi_after | string | |
| lifecycle | string | IDEA|DESIGNING|IN_DEVELOPMENT; LAUNCHED only via update_solution. |
| target_id | string | |
| agent_name | string | Signs comments/assignments/decisions. |
| hold_token | string | Execution proof for a live hold; renewals and moves need the take response value. |
| kpi_before | string | |
| risk_notes | array | Unresolved contradictions acknowledged by id. |
| scope_kind | string | agent_scope register: map = whole taxonomy map; node = one anchor. |
| snippet_id | string | |
| updated_at | string | Optimistic lock; stale edits fail STALE_DATA. |
| description | string | create_solution only; update_solution refuses it. |
| document_id | string | |
| instruction | string | |
| observed_at | string | |
| review_kind | string | one of ["signal_triage","claim_structure","solution_quality"] |
| scope_value | string | agent_scope register: the map id or node id covered. |
| snooze_days | number | |
| solution_id | string | Solution UUID (from a name or SEN-n: atisbo_lookup mode=resolve) |
| target_type | string | one of ["claim","solution","snippet","tenant","pm_context","node","edge","map","chat_session","context_document","mcp_connection","mcp_server_key","decision_signal","integration","workspace","access_link"] |
| alternatives | array | |
| out_of_scope | array | check_coverage: claim/idea UUIDs intentionally NOT addressed — one UUID per row, not prose (a sentence is not an id and dies at the transport). |
| product_name | string | |
| snooze_clear | boolean | |
| term_minutes | number | claim_hold mins (dispatch 120) |
| clear_discard | boolean | |
| covered_ideas | array | check_coverage: idea ids in the coverage map. |
| decision_type | string | log_decision: e.g. product_decision, note; full list in the error. |
| evidence_refs | array | record_outcome: evidence refs. |
| main_features | array | |
| merged_commit | string | update_solution/deliver/validate_delivery: landed commit sha. |
| assign_node_id | string | update_solution: taxonomy node. |
…and 33 more parameters.
{
"name": "atisbo_decide",
"title": "Decide: product decisions and delivery closure",
"description": "CURATE: evidence review/grouping, deal-breakers. EXECUTE: create, update, dispatch or delete Solutions, record Outcomes. DOCUMENT/GOVERN: living docs, coverage, schedules, knowledge, strategy. log_decision is only for external decisions; mutations log themselves. Writes require UUIDs. mode=declare_pm_exception marks a CLAIM as needing a human decision.",
"inputSchema": {
"type": "object",
"required": [
"mode"
],
"properties": {
"id": {
"type": "string",
"format": "uuid",
"description": "delete_knowledge/set_knowledge_category doc id."
},
"mode": {
"type": "string",
"description": "Resolve names to UUIDs before mutating; notes per mode in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest."
},
"note": {
"type": "string",
"maxLength": 5000,
"description": "record_outcome note; triage/log_decision rationale."
},
"spec": {
"type": "object",
"required": [
"problem",
"evidence",
"hypothesis",
"successCriteria"
],
"properties": {
"files": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 50,
"description": "One repo path per row, optionally anchored (:line or :start-end, e.g. path/to/file.ts:1200-1450). A file this work creates carries a trailing (new) marker, e.g. path/to/file.ts (new) — created files need no anchor and get no line nudge."
},
"problem": {
"type": "string",
"maxLength": 5000
},
"evidence": {
"type": "array",
"items": {
"type": "string",
"maxLength": 1000
},
"maxItems": 30
},
"proposal": {
"type": "string",
"maxLength": 5000,
"description": "What we will build; distinct from hypothesis."
},
"hypothesis": {
"type": "string",
"maxLength": 5000
},
"constraints": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 50
},
"decisionLog": {
"type": "object",
"required": [
"alternatives",
"reasoning"
],
"properties": {
"reasoning": {
"type": "string",
"maxLength": 5000
},
"assumptions": {
"type": "string",
"maxLength": 3000
},
"alternatives": {
"type": "array",
"items": {
"type": "string",
"maxLength": 1000
},
"maxItems": 20
}
}
},
"successCriteria": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
],
"description": "What must be TRUE at launch: one string, or a list of criterion strings (joined with newlines). Template: implementation_context."
}
}
},
"brief": {
"type": "string",
"maxLength": 20000,
"description": "dispatch_solution: agent brief."
},
"force": {
"type": "boolean",
"description": "Confirms an irreversible write (reassign_snippet moves that empty a claim; combine_claims merges). Re-send the refused call unchanged plus force:true."
},
"reach": {
"description": "record_reach: {affected_users, base_users, base_definition, scope, segment?, method, source?, confidence?, measured_at?, measured_by?}."
},
"title": {
"type": "string",
"maxLength": 500
},
"effort": {
"type": "number",
"maximum": 52,
"minimum": 0.5,
"description": "Size estimate, person-weeks (never affects order)."
},
"matrix": {
"type": "array",
"items": {
"type": "object",
"required": [
"criterion",
"status"
],
"properties": {
"note": {
"type": "string",
"maxLength": 500,
"description": "Required for incomplete: alternative method, or blocker."
},
"status": {
"enum": [
"preview_verified",
"production_verified",
"ci_verified",
"pm_confirmed",
"not_applicable",
"incomplete",
"superseded"
],
"type": "string"
},
"evidence": {
"type": "string",
"maxLength": 500,
"description": "What you did and saw; required for *_verified."
},
"criterion": {
"type": "string",
"maxLength": 200,
"description": "Criterion, in the living doc's words."
},
"work_type": {
"enum": [
"code",
"migration"
],
"type": "string",
"description": "Kind of work this criterion proves. Omit for code. A migration row only resolves through production_verified or a person's pm_confirmed."
},
"evidence_refs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 300
},
"maxItems": 10,
"description": "Durable refs: PR, dashboard, log."
},
"requires_person": {
"type": "boolean",
"description": "Once true, only a person's pm_confirmed resolves this row."
}
}
},
"maxItems": 20,
"description": "validate_delivery / deliver: one entry per criterion."
},
"pr_url": {
"type": "string",
"format": "uri",
"maxLength": 500
},
"reason": {
"type": "string",
"maxLength": 500,
"description": "Why: ≤500 chars — longer text is refused, state the decision not the history."
},
"status": {
"enum": [
"signal",
"noise",
"review"
],
"type": "string",
"description": "Target classification."
},
"comment": {
"type": "string",
"maxLength": 10000,
"description": "update_solution/deliver/dispatch: thread report."
},
"hold_op": {
"enum": [
"take",
"renew",
"release",
"revoke",
"assign",
"unassign"
],
"type": "string",
"description": "take | renew (holder) | release (holder) | revoke (PM force) | assign (names who it is for, scope-gated) | unassign."
},
"mission": {
"type": "string",
"maxLength": 2000,
"description": "update_strategy: informational only."
},
"node_id": {
"type": "string",
"format": "uuid"
},
"outcome": {
"enum": [
"success",
"partial",
"miss",
"unexpected"
],
"type": "string",
"description": "record_outcome: launch impact."
},
"roadmap": {
"type": "string",
"maxLength": 5000,
"description": "update_strategy: informational only."
},
"verdict": {
"enum": [
"real_fixed",
"noise",
"proceed",
"defer",
"drop"
],
"type": "string",
"description": "triage closes; log_decision takes the judgement answer."
},
"category": {
"type": "string",
"maxLength": 60,
"description": "set_knowledge_category; update_solution refuses it."
},
"claim_id": {
"type": "string",
"format": "uuid",
"description": "Claim UUID (atisbo_lookup mode=resolve)"
},
"decision": {
"type": "string",
"maxLength": 500,
"description": "max 500 chars."
},
"scope_op": {
"enum": [
"register",
"unregister",
"list"
],
"type": "string",
"description": "agent_scope verb: register | unregister | list."
},
"strategy": {
"type": "string",
"maxLength": 5000,
"description": "update_strategy: the only functional field."
},
"unassign": {
"type": "boolean"
},
"assign_to": {
"type": "string",
"maxLength": 120,
"description": "claim_hold op=assign target: who the claim is for."
},
"claim_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
},
"maxItems": 50
},
"for_agent": {
"type": "string",
"maxLength": 120,
"description": "agent_scope: whose scope (register/unregister target, list filter)."
},
"kpi_after": {
"type": "string",
"maxLength": 200
},
"lifecycle": {
"type": "string",
"description": "IDEA|DESIGNING|IN_DEVELOPMENT; LAUNCHED only via update_solution."
},
"target_id": {
"type": "string",
"format": "uuid"
},
"agent_name": {
"type": "string",
"maxLength": 120,
"description": "Signs comments/assignments/decisions."
},
"hold_token": {
"type": "string",
"maxLength": 128,
"minLength": 32,
"description": "Execution proof for a live hold; renewals and moves need the take response value."
},
"kpi_before": {
"type": "string",
"maxLength": 200
},
"risk_notes": {
"type": "array",
"items": {
"type": "string",
"maxLength": 1000
},
"maxItems": 50,
"description": "Unresolved contradictions acknowledged by id."
},
"scope_kind": {
"enum": [
"map",
"node"
],
"type": "string",
"description": "agent_scope register: map = whole taxonomy map; node = one anchor."
},
"snippet_id": {
"type": "string",
"format": "uuid"
},
"updated_at": {
"type": "string",
"description": "Optimistic lock; stale edits fail STALE_DATA."
},
"description": {
"type": "string",
"maxLength": 2000,
"description": "create_solution only; update_solution refuses it."
},
"document_id": {
"type": "string",
"format": "uuid"
},
"instruction": {
"type": "string",
"maxLength": 2000
},
"observed_at": {
"type": "string",
"format": "date-time"
},
"review_kind": {
"enum": [
"signal_triage",
"claim_structure",
"solution_quality"
],
"type": "string"
},
"scope_value": {
"type": "string",
"format": "uuid",
"description": "agent_scope register: the map id or node id covered."
},
"snooze_days": {
"type": "number"
},
"solution_id": {
"type": "string",
"format": "uuid",
"description": "Solution UUID (from a name or SEN-n: atisbo_lookup mode=resolve)"
},
"target_type": {
"enum": [
"claim",
"solution",
"snippet",
"tenant",
"pm_context",
"node",
"edge",
"map",
"chat_session",
"context_document",
"mcp_connection",
"mcp_server_key",
"decision_signal",
"integration",
"workspace",
"access_link"
],
"type": "string"
},
"alternatives": {
"type": "array",
"items": {
"type": "string",
"maxLength": 1000
},
"maxItems": 20
},
"out_of_scope": {
"type": "array",
"items": {
"type": "string",
"maxLength": 128
},
"maxItems": 100,
"description": "check_coverage: claim/idea UUIDs intentionally NOT addressed — one UUID per row, not prose (a sentence is not an id and dies at the transport)."
},
"product_name": {
"type": "string",
"maxLength": 200
},
"snooze_clear": {
"type": "boolean"
},
"term_minutes": {
"type": "number",
"maximum": 240,
"minimum": 1,
"description": "claim_hold mins (dispatch 120)"
},
"clear_discard": {
"type": "boolean"
},
"covered_ideas": {
"type": "array",
"items": {
"type": "string",
"maxLength": 128
},
"maxItems": 100,
"description": "check_coverage: idea ids in the coverage map."
},
"decision_type": {
"type": "string",
"maxLength": 60,
"description": "log_decision: e.g. product_decision, note; full list in the error."
},
"evidence_refs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 20,
"description": "record_outcome: evidence refs."
},
"main_features": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"description"
],
"properties": {
"name": {
"type": "string",
"maxLength": 200
},
"description": {
"type": "string",
"maxLength": 1000
}
}
}
},
"merged_commit": {
"type": "string",
"description": "update_solution/deliver/validate_delivery: landed commit sha."
},
"assign_node_id": {
"type": "string",
"format": "uuid",
"description": "update_solution: taxonomy node."
},
"covered_claims": {
"type": "array",
"items": {
"type": "string",
"maxLength": 128
},
"maxItems": 50,
"description": "check_coverage: claim ids this work implements."
},
"deployment_url": {
"type": "string",
"format": "uri",
"maxLength": 500,
"description": "deliver: URL of that deploy."
},
"design_context": {
"type": "string",
"maxLength": 8000
},
"discard_reason": {
"type": "string",
"maxLength": 500,
"description": "Divergence loser (ADR-224); CANCELED required (≤500 chars)."
},
"force_reassign": {
"type": "boolean",
"description": "Audited takeover of a Solution in progress."
},
"metric_current": {
"type": "number",
"description": "record_outcome (automated): fresh metric reading."
},
"no_code_reason": {
"type": "string",
"maxLength": 500,
"description": "deliver: why no code shipped."
},
"pm_instruction": {
"type": "string",
"maxLength": 1000,
"description": "update_strategy: the PM's request, quoted."
},
"priority_boost": {
"type": "number",
"maximum": 5,
"minimum": 0.5,
"description": "PM multiplier over evidence-weighted priority."
},
"assign_to_agent": {
"type": "boolean",
"description": "update_solution: take ownership."
},
"deployed_commit": {
"type": "string",
"description": "deliver: sha running in production."
},
"is_deal_breaker": {
"type": "boolean",
"description": "true = confirm/flag, false = reject/unflag."
},
"target_claim_id": {
"type": "string",
"format": "uuid",
"description": "Claim UUID (atisbo_lookup mode=resolve)"
},
"attach_claim_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
},
"maxItems": 20
},
"coverage_updates": {
"description": "deliver: buckets snippets/ideas/claims."
},
"detach_claim_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
},
"maxItems": 20
},
"refresh_schedule": {
"enum": [
"none",
"hourly",
"daily",
"weekly",
"biweekly",
"monthly"
],
"type": "string"
},
"client_request_id": {
"type": "string",
"maxLength": 200,
"minLength": 8,
"description": "Retry handle: same key replays, never duplicates."
},
"criteria_left_out": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 20,
"description": "Criteria left OUT (ADR-234); only with LAUNCHED."
},
"expected_behavior": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 50,
"description": "check_coverage: observable behavior delivered."
},
"replace_confirmed": {
"type": "boolean",
"description": "true confirms a shorter matrix replacing a longer one."
},
"snooze_indefinite": {
"type": "boolean",
"description": "snooze_claim only; update_solution refuses it."
},
"chosen_solution_id": {
"type": "string",
"format": "uuid",
"description": "update_solution: the winning sibling."
},
"clear_pm_exception": {
"type": "boolean"
},
"outcome_confidence": {
"enum": [
"high",
"medium",
"low"
],
"type": "string"
},
"on_behalf_of_person": {
"type": "boolean"
},
"pm_exception_reason": {
"type": "string",
"maxLength": 1000,
"description": "a PERSON's choice; requires alternatives (≥2 distinct options). Blockers → operational_block_reason."
},
"verification_method": {
"type": "string",
"maxLength": 500,
"description": "record_outcome: how verified (max 500 chars)."
},
"contradictions_found": {
"type": "boolean",
"description": "record_outcome (automated): attest a contradiction sweep."
},
"clear_operational_block": {
"type": "boolean"
},
"criteria_left_out_reason": {
"type": "string",
"maxLength": 1000,
"description": "Why each is out; required with criteria_left_out."
},
"operational_block_reason": {
"type": "string",
"maxLength": 500,
"description": "update_solution: operational blocker; not a decision (≤500 chars)."
},
"operational_block_category": {
"enum": [
"credentials",
"permissions",
"budget",
"provider_capacity",
"external_dependency"
],
"type": "string"
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"result": {}
}
},
"annotations": {
"category": "write",
"readOnlyHint": false,
"strict_output": false,
"destructiveHint": true,
"supports_cursor": false,
"supports_idempotency": true,
"requires_confirmation": false,
"supports_since_checkpoint": false
}
}Create/apply maps, generate/edit nodes and edges, anchor claims/snippets, bind metrics, manage claim-snipe maps, regroup (merge/split), build_macros (macros, preview first). Prefer mode=apply for MECE grouping. Anchor and link_claims put a claim on a node differently and both refuse the wrong map kind: anchor sets the TAXONOMY category (auto_node_id); link_claims adds STRUCTURAL-map membership.
| Parameter | Type | Description |
|---|---|---|
| mode * | string | Per-mode notes in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest. |
| name | string | Map, node, or metric name. |
| note | string | link_claims: rationale stored on every link. |
| label | string | |
| level | number | Node hierarchy depth. |
| map_id | string | Map UUID. |
| anchors | array | Batch claim anchors. |
| edge_id | string | Edge UUID for delete_edge mode. |
| node_id | string | Node UUID. |
| preview | boolean | regroup/build_macros: read-only preview. |
| branches | array | Branches for apply mode. |
| claim_id | string | Claim UUID (atisbo_lookup mode=resolve) |
| map_type | string | one of ["taxonomy","kpi_tree","ost","custom"] |
| provider | string | Metric provider: posthog, amplitude, stripe, manual… |
| template | string | one of ["taxonomy","metric_tree","goal_tree","opportunity_solution_tree","freeform"] |
| claim_ids | array | link_claims: claims to place under node_id. |
| direction | string | regroup: broader merges; specific splits. |
| edge_type | string | one of ["causal","sequential","associative"] |
| new_level | number | New depth after a move. |
| parent_id | string | Parent node UUID. |
| binding_id | string | metric_update: binding id (lookup get, metrics[].id). |
| event_name | string | |
| snippet_id | string | |
| updated_at | string | metric_update: updated_at from your last read. |
| assignments | array | |
| description | string | Map/node/branch description. |
| metric_name | string | |
| metric_type | string | one of ["input","north_star","business_kpi"] |
| target_value | number | |
| current_value | number | metric_update: today's value; same-day re-entry replaces it. |
| grouping_mode | string | one of ["classification","mece","tasks","journey","severity","custom"] |
| new_parent_id | string | Move target parent; null promotes to root. |
| regroup_level | string | regroup broader: merge aggressiveness. |
| source_map_id | string | |
| branch_options | array | |
| source_node_id | string | |
| target_node_id | string | |
| workspace_wide | boolean | regroup: explicit YES to run WORKSPACE-WIDE. |
| context_answers | object | Grounding answers for AI map generation. |
| historical_data | array | metric_update: full series REPLACEMENT. |
| time_range_days | number | |
| target_threshold | number | regroup direction=specific: split threshold. |
{
"name": "atisbo_map",
"title": "Map: product map nodes and edges",
"description": "Create/apply maps, generate/edit nodes and edges, anchor claims/snippets, bind metrics, manage claim-snipe maps, regroup (merge/split), build_macros (macros, preview first). Prefer mode=apply for MECE grouping. Anchor and link_claims put a claim on a node differently and both refuse the wrong map kind: anchor sets the TAXONOMY category (auto_node_id); link_claims adds STRUCTURAL-map membership.",
"inputSchema": {
"type": "object",
"required": [
"mode"
],
"properties": {
"mode": {
"type": "string",
"description": "Per-mode notes in meta.guidance. Open string (new modes work with a cached tools/list); unknown mode? invalid_params[].allowed_values names the nearest."
},
"name": {
"type": "string",
"maxLength": 200,
"description": "Map, node, or metric name."
},
"note": {
"type": "string",
"maxLength": 500,
"description": "link_claims: rationale stored on every link."
},
"label": {
"type": "string",
"maxLength": 100
},
"level": {
"type": "number",
"maximum": 5,
"minimum": 1,
"description": "Node hierarchy depth."
},
"map_id": {
"type": "string",
"format": "uuid",
"description": "Map UUID."
},
"anchors": {
"type": "array",
"items": {
"type": "object",
"properties": {
"node_id": {
"type": "string",
"format": "uuid"
},
"claim_id": {
"type": "string",
"format": "uuid"
}
}
},
"maxItems": 200,
"description": "Batch claim anchors."
},
"edge_id": {
"type": "string",
"format": "uuid",
"description": "Edge UUID for delete_edge mode."
},
"node_id": {
"type": "string",
"format": "uuid",
"description": "Node UUID."
},
"preview": {
"type": "boolean",
"description": "regroup/build_macros: read-only preview."
},
"branches": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"maxLength": 200
},
"claim_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
},
"maxItems": 500
},
"description": {
"type": "string",
"maxLength": 2000,
"description": "Branch description."
}
}
},
"maxItems": 50,
"description": "Branches for apply mode."
},
"claim_id": {
"type": "string",
"format": "uuid",
"description": "Claim UUID (atisbo_lookup mode=resolve)"
},
"map_type": {
"enum": [
"taxonomy",
"kpi_tree",
"ost",
"custom"
],
"type": "string"
},
"provider": {
"type": "string",
"description": "Metric provider: posthog, amplitude, stripe, manual…"
},
"template": {
"enum": [
"taxonomy",
"metric_tree",
"goal_tree",
"opportunity_solution_tree",
"freeform"
],
"type": "string"
},
"claim_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
},
"maxItems": 200,
"description": "link_claims: claims to place under node_id."
},
"direction": {
"enum": [
"broader",
"specific"
],
"type": "string",
"description": "regroup: broader merges; specific splits."
},
"edge_type": {
"enum": [
"causal",
"sequential",
"associative"
],
"type": "string"
},
"new_level": {
"type": "number",
"maximum": 5,
"minimum": 1,
"description": "New depth after a move."
},
"parent_id": {
"type": "string",
"format": "uuid",
"description": "Parent node UUID."
},
"binding_id": {
"type": "string",
"format": "uuid",
"description": "metric_update: binding id (lookup get, metrics[].id)."
},
"event_name": {
"type": "string",
"maxLength": 200
},
"snippet_id": {
"type": "string",
"format": "uuid"
},
"updated_at": {
"type": "string",
"format": "date-time",
"description": "metric_update: updated_at from your last read."
},
"assignments": {
"type": "array",
"items": {
"type": "object",
"properties": {
"branchKey": {
"type": "string",
"maxLength": 120
},
"snippetId": {
"type": "string",
"format": "uuid"
},
"branchName": {
"type": "string",
"maxLength": 200
},
"branch_key": {
"type": "string",
"maxLength": 120
},
"snippet_id": {
"type": "string",
"format": "uuid"
},
"branch_name": {
"type": "string",
"maxLength": 200
}
},
"description": "One snippet per L2 branch: snippet_id + branch_key."
},
"maxItems": 500
},
"description": {
"type": "string",
"maxLength": 2000,
"description": "Map/node/branch description."
},
"metric_name": {
"type": "string",
"maxLength": 200
},
"metric_type": {
"enum": [
"input",
"north_star",
"business_kpi"
],
"type": "string"
},
"target_value": {
"type": "number"
},
"current_value": {
"type": "number",
"description": "metric_update: today's value; same-day re-entry replaces it."
},
"grouping_mode": {
"enum": [
"classification",
"mece",
"tasks",
"journey",
"severity",
"custom"
],
"type": "string"
},
"new_parent_id": {
"type": "string",
"format": "uuid",
"description": "Move target parent; null promotes to root."
},
"regroup_level": {
"enum": [
"conservative",
"moderate",
"aggressive"
],
"type": "string",
"description": "regroup broader: merge aggressiveness."
},
"source_map_id": {
"type": "string",
"format": "uuid"
},
"branch_options": {
"type": "array",
"items": {
"type": "object",
"required": [
"key",
"label"
],
"properties": {
"key": {
"type": "string",
"maxLength": 120
},
"label": {
"type": "string",
"maxLength": 200
}
}
},
"maxItems": 20
},
"source_node_id": {
"type": "string",
"format": "uuid"
},
"target_node_id": {
"type": "string",
"format": "uuid"
},
"workspace_wide": {
"type": "boolean",
"description": "regroup: explicit YES to run WORKSPACE-WIDE."
},
"context_answers": {
"type": "object",
"properties": {},
"description": "Grounding answers for AI map generation."
},
"historical_data": {
"type": "array",
"items": {
"type": "object",
"required": [
"date",
"value"
],
"properties": {
"date": {
"type": "string"
},
"value": {
"type": "number"
}
}
},
"maxItems": 365,
"description": "metric_update: full series REPLACEMENT."
},
"time_range_days": {
"type": "number"
},
"target_threshold": {
"type": "number",
"maximum": 0.98,
"minimum": 0.5,
"description": "regroup direction=specific: split threshold."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"result": {}
}
},
"annotations": {
"category": "write",
"readOnlyHint": false,
"strict_output": false,
"destructiveHint": true,
"supports_cursor": false,
"supports_idempotency": true,
"requires_confirmation": false,
"supports_since_checkpoint": false
}
}WHERE Atisbo gets its signals. Modes: list, catalog, create (returns endpoint), configure, pause, resume, sync_now, delete (soft-disconnect). THE CATALOG IS NOT THE BOUNDARY: almost anything connects — call catalog and read `fallback` before saying "Atisbo cannot ingest that". Atisbo only READS a connected system. create returns the signing secret shown ONCE — relay to the human immediately.
| Parameter | Type | Description |
|---|---|---|
| kind | string | mode=create: "email" provisions the ingest address; default webhook. |
| mode | string | list/catalog need no ids; others need connection_id or create fields. |
| label | string | create/configure: human name for the source, e.g. "Freshdesk". |
| query | string | mode=catalog only: filter by name, category or description. |
| config | object | create with provider: catalog required_fields; stored encrypted. |
| toolkit | string | composio action modes: Composio app slug (e.g. "freshdesk"). |
| provider | string | mode=create: NATIVE provider from catalog native_providers (with config). |
| pull_tool | string | composio_create: read-only daily action from composio_actions. |
| recipe_id | string | mode=create: catalog recipe id (curated mapping). |
| json_paths | object | create/configure: dotted paths into the payload body. |
| rate_limit | number | create/configure: max requests/min accepted. Default 100. |
| sync_every | string | PULL sources only: cadence. Default daily. |
| trigger_slug | string | composio_create, INSTANT apps: trigger from composio_catalog. |
| connection_id | string | Connection id (mode=list); required by configure/pause/resume/sync_now/delete. |
| pull_arguments | object | composio_create with pull_tool: action arguments. |
| collection_path | string | composio_create + pull_tool: dotted path to the record array. |
| source_category | string | mode=create with your own mapping: what the payload carries. |
| skip_attribution | boolean | create: anonymous public-forum sources have no attributable customer. |
{
"name": "atisbo_connect",
"title": "Connect: intake source configuration",
"description": "WHERE Atisbo gets its signals. Modes: list, catalog, create (returns endpoint), configure, pause, resume, sync_now, delete (soft-disconnect). THE CATALOG IS NOT THE BOUNDARY: almost anything connects — call catalog and read `fallback` before saying \"Atisbo cannot ingest that\". Atisbo only READS a connected system. create returns the signing secret shown ONCE — relay to the human immediately.",
"inputSchema": {
"type": "object",
"properties": {
"kind": {
"enum": [
"webhook",
"email"
],
"type": "string",
"description": "mode=create: \"email\" provisions the ingest address; default webhook."
},
"mode": {
"enum": [
"list",
"catalog",
"create",
"configure",
"pause",
"resume",
"sync_now",
"delete",
"composio_catalog",
"composio_actions",
"composio_create",
"composio_authorize"
],
"type": "string",
"description": "list/catalog need no ids; others need connection_id or create fields."
},
"label": {
"type": "string",
"maxLength": 120,
"description": "create/configure: human name for the source, e.g. \"Freshdesk\"."
},
"query": {
"type": "string",
"maxLength": 100,
"description": "mode=catalog only: filter by name, category or description."
},
"config": {
"type": "object",
"properties": {},
"description": "create with provider: catalog required_fields; stored encrypted."
},
"toolkit": {
"type": "string",
"maxLength": 80,
"description": "composio action modes: Composio app slug (e.g. \"freshdesk\")."
},
"provider": {
"type": "string",
"maxLength": 40,
"description": "mode=create: NATIVE provider from catalog native_providers (with config)."
},
"pull_tool": {
"type": "string",
"maxLength": 120,
"description": "composio_create: read-only daily action from composio_actions."
},
"recipe_id": {
"type": "string",
"maxLength": 100,
"description": "mode=create: catalog recipe id (curated mapping)."
},
"json_paths": {
"type": "object",
"required": [
"raw_text"
],
"properties": {
"source": {
"type": "string"
},
"channel": {
"type": "string"
},
"user_id": {
"type": "string",
"description": "Path to who said it — enables company attribution."
},
"raw_text": {
"type": "string",
"description": "REQUIRED: path to the customer's own words, e.g. \"ticket.description\"."
},
"occurred_at": {
"type": "string",
"description": "Path to the timestamp; else ingestion time."
},
"deep_link_url": {
"type": "string",
"description": "Path to a URL opening the item in the origin tool."
},
"native_object_id": {
"type": "string"
},
"native_revision_id": {
"type": "string"
}
},
"description": "create/configure: dotted paths into the payload body."
},
"rate_limit": {
"type": "number",
"maximum": 10000,
"description": "create/configure: max requests/min accepted. Default 100."
},
"sync_every": {
"enum": [
"hourly",
"daily",
"weekly"
],
"type": "string",
"description": "PULL sources only: cadence. Default daily."
},
"trigger_slug": {
"type": "string",
"maxLength": 120,
"description": "composio_create, INSTANT apps: trigger from composio_catalog."
},
"connection_id": {
"type": "string",
"format": "uuid",
"description": "Connection id (mode=list); required by configure/pause/resume/sync_now/delete."
},
"pull_arguments": {
"type": "object",
"properties": {},
"description": "composio_create with pull_tool: action arguments."
},
"collection_path": {
"type": "string",
"maxLength": 200,
"description": "composio_create + pull_tool: dotted path to the record array."
},
"source_category": {
"enum": [
"conversation_message",
"survey_response",
"document_revision",
"transcript_session",
"operational_event"
],
"type": "string",
"description": "mode=create with your own mapping: what the payload carries."
},
"skip_attribution": {
"type": "boolean",
"description": "create: anonymous public-forum sources have no attributable customer."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"result": {}
}
},
"annotations": {
"category": "write",
"readOnlyHint": false,
"strict_output": false,
"destructiveHint": true,
"supports_cursor": false,
"supports_idempotency": true,
"requires_confirmation": false,
"supports_since_checkpoint": false
}
}Broad analytical query over claims, solutions, or activity: time filters, grouping, metrics, ready-to-render chart artifact. Use FIRST for analytical questions spanning entities or time windows; a single-entity drill-down is atisbo_lookup mode=get with the entity id.
| Parameter | Type | Description |
|---|---|---|
| limit | number | Max grouped rows; over-asks clamp. |
| cursor | string | From stream.next_cursor — pages grouped rows beyond `limit`. |
| domain | string | Free-text product area, resolved to map nodes. |
| filters | object | Filters: AND across fields, OR within a field. |
| metrics | array | Aggregate metrics per group (1-4). |
| subject | string | claims (opportunities), solutions, or activity (decisions + events). |
| analysis | string | summary, table, or chart kind (bar/line/scatter); trend=line. |
| group_by | array | Row grouping dimensions (1-2). |
| time_range | object | 7d/30d/90d preset or from/to ISO dates; default 30d. |
{
"name": "atisbo_analyze",
"title": "Analyze: aggregates over the corpus",
"description": "Broad analytical query over claims, solutions, or activity: time filters, grouping, metrics, ready-to-render chart artifact. Use FIRST for analytical questions spanning entities or time windows; a single-entity drill-down is atisbo_lookup mode=get with the entity id.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "number",
"minimum": 1,
"description": " Max grouped rows; over-asks clamp."
},
"cursor": {
"type": "string",
"description": "From stream.next_cursor — pages grouped rows beyond `limit`."
},
"domain": {
"type": "string",
"maxLength": 120,
"minLength": 2,
"description": "Free-text product area, resolved to map nodes."
},
"filters": {
"type": "object",
"properties": {
"sources": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20,
"description": "Transport, not provenance; claim/solution aggregates ignore it."
},
"node_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
},
"maxItems": 20
},
"claim_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
},
"maxItems": 50
},
"lifecycle": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"description": "Known lifecycle stages (case-insensitive)."
},
"claim_status": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"description": "Known claim statuses (case-insensitive)."
},
"signal_origin": {
"type": "array",
"items": {
"enum": [
"customer",
"internal",
"operational"
],
"type": "string"
},
"maxItems": 3,
"description": "customer | internal | operational — claim matches if ANY snippet does."
}
},
"description": "Filters: AND across fields, OR within a field."
},
"metrics": {
"type": "array",
"items": {
"enum": [
"claim_count",
"snippet_count",
"avg_power_score",
"decision_count",
"activity_count",
"effort_proxy_avg",
"solution_count"
],
"type": "string",
"description": "Aggregate metric computed per group."
},
"maxItems": 4,
"description": "Aggregate metrics per group (1-4)."
},
"subject": {
"enum": [
"claims",
"solutions",
"activity",
"opportunities"
],
"type": "string",
"description": "claims (opportunities), solutions, or activity (decisions + events)."
},
"analysis": {
"enum": [
"summary",
"table",
"bar",
"line",
"scatter",
"trend"
],
"type": "string",
"description": "summary, table, or chart kind (bar/line/scatter); trend=line."
},
"group_by": {
"type": "array",
"items": {
"enum": [
"claim",
"node",
"day",
"week",
"status",
"source",
"lifecycle"
],
"type": "string",
"description": "Row grouping dimension. lifecycle is an alias for status."
},
"maxItems": 2,
"description": "Row grouping dimensions (1-2)."
},
"time_range": {
"type": "object",
"properties": {
"to": {
"type": "string"
},
"from": {
"type": "string"
},
"preset": {
"enum": [
"7d",
"30d",
"90d"
],
"type": "string",
"description": "Relative window preset."
}
},
"description": "7d/30d/90d preset or from/to ISO dates; default 30d."
}
}
},
"outputSchema": {
"type": "object",
"required": [
"data",
"meta"
],
"properties": {
"data": {
"type": "object",
"required": [
"resolved_query",
"summary",
"dataset",
"sources",
"warnings",
"assumptions"
],
"properties": {
"chart": {
"type": "object",
"required": [
"kind",
"title",
"x_key",
"y_key"
],
"properties": {
"kind": {
"enum": [
"bar",
"line",
"scatter"
],
"type": "string"
},
"title": {
"type": "string"
},
"x_key": {
"type": "string"
},
"y_key": {
"type": "string"
},
"series_key": {
"type": "string"
}
}
},
"stream": {
"type": "object",
"required": [
"checkpoint",
"has_more"
],
"properties": {
"has_more": {
"type": "boolean"
},
"checkpoint": {
"type": "string"
},
"next_cursor": {
"type": "string"
}
}
},
"dataset": {
"type": "object",
"required": [
"columns",
"rows",
"row_count"
],
"properties": {
"rows": {
"type": "array",
"items": {
"type": "object",
"properties": {}
}
},
"columns": {
"type": "array",
"items": {
"type": "string"
}
},
"row_count": {
"type": "number",
"minimum": 0
},
"total_rows": {
"type": "number",
"minimum": 0
}
}
},
"sources": {
"type": "object",
"required": [
"views_used",
"row_count"
],
"properties": {
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"row_count": {
"type": "number",
"minimum": 0
},
"views_used": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"summary": {
"type": "string"
},
"artifact": {
"type": "object",
"required": [
"artifact_type",
"artifact_data"
],
"properties": {
"artifact_data": {
"type": "object",
"required": [
"title",
"summary",
"resolved_query",
"dataset",
"sources",
"warnings",
"assumptions"
],
"properties": {
"chart": {
"type": "object",
"required": [
"kind",
"title",
"x_key",
"y_key"
],
"properties": {
"kind": {
"enum": [
"bar",
"line",
"scatter"
],
"type": "string"
},
"title": {
"type": "string"
},
"x_key": {
"type": "string"
},
"y_key": {
"type": "string"
},
"series_key": {
"type": "string"
}
}
},
"title": {
"type": "string"
},
"dataset": {
"type": "object",
"required": [
"columns",
"rows",
"row_count"
],
"properties": {
"rows": {
"type": "array",
"items": {
"type": "object",
"properties": {}
}
},
"columns": {
"type": "array",
"items": {
"type": "string"
}
},
"row_count": {
"type": "number",
"minimum": 0
},
"total_rows": {
"type": "number",
"minimum": 0
}
}
},
"sources": {
"type": "object",
"required": [
"views_used",
"row_count"
],
"properties": {
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"row_count": {
"type": "number",
"minimum": 0
},
"views_used": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"summary": {
"type": "string"
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
},
"resolved_query": {
"type": "object",
"required": [
"subject",
"time_range",
"group_by",
"metrics",
"analysis",
"filters",
"resolved_nodes"
],
"properties": {
"domain": {
"type": "string"
},
"filters": {
"type": "object",
"properties": {
"sources": {
"type": "array",
"items": {
"type": "string"
}
},
"node_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"claim_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"lifecycle": {
"type": "array",
"items": {
"type": "string"
}
},
"claim_status": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"metrics": {
"type": "array",
"items": {
"enum": [
"claim_count",
"snippet_count",
"avg_power_score",
"decision_count",
"activity_count",
"effort_proxy_avg",
"solution_count"
],
"type": "string",
"description": "Aggregate metric computed per group."
}
},
"subject": {
"enum": [
"claims",
"solutions",
"activity",
"opportunities"
],
"type": "string",
"description": "claims (opportunities), solutions, or activity (decisions + events)."
},
"analysis": {
"enum": [
"summary",
"table",
"bar",
"line",
"scatter",
"trend"
],
"type": "string",
"description": "summary, table, or chart kind (bar/line/scatter); trend=line."
},
"group_by": {
"type": "array",
"items": {
"enum": [
"claim",
"node",
"day",
"week",
"status",
"source",
"lifecycle"
],
"type": "string",
"description": "Row grouping dimension. lifecycle is an alias for status."
}
},
"time_range": {
"type": "object",
"required": [
"from",
"to",
"timezone",
"preset"
],
"properties": {
"to": {
"type": "string"
},
"from": {
"type": "string"
},
"preset": {
"enum": [
"7d",
"30d",
"90d",
"custom"
],
"type": "string"
},
"timezone": {
"type": "string"
}
}
},
"resolved_nodes": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"name"
],
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"score": {
"type": "number"
}
}
}
}
}
}
}
},
"artifact_type": {
"enum": [
"analytics-report"
],
"type": "string"
}
}
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
},
"resolved_query": {
"type": "object",
"required": [
"subject",
"time_range",
"group_by",
"metrics",
"analysis",
"filters",
"resolved_nodes"
],
"properties": {
"domain": {
"type": "string"
},
"filters": {
"type": "object",
"properties": {
"sources": {
"type": "array",
"items": {
"type": "string"
}
},
"node_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"claim_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"lifecycle": {
"type": "array",
"items": {
"type": "string"
}
},
"claim_status": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"metrics": {
"type": "array",
"items": {
"enum": [
"claim_count",
"snippet_count",
"avg_power_score",
"decision_count",
"activity_count",
"effort_proxy_avg",
"solution_count"
],
"type": "string",
"description": "Aggregate metric computed per group."
}
},
"subject": {
"enum": [
"claims",
"solutions",
"activity",
"opportunities"
],
"type": "string",
"description": "claims (opportunities), solutions, or activity (decisions + events)."
},
"analysis": {
"enum": [
"summary",
"table",
"bar",
"line",
"scatter",
"trend"
],
"type": "string",
"description": "summary, table, or chart kind (bar/line/scatter); trend=line."
},
"group_by": {
"type": "array",
"items": {
"enum": [
"claim",
"node",
"day",
"week",
"status",
"source",
"lifecycle"
],
"type": "string",
"description": "Row grouping dimension. lifecycle is an alias for status."
}
},
"time_range": {
"type": "object",
"required": [
"from",
"to",
"timezone",
"preset"
],
"properties": {
"to": {
"type": "string"
},
"from": {
"type": "string"
},
"preset": {
"enum": [
"7d",
"30d",
"90d",
"custom"
],
"type": "string"
},
"timezone": {
"type": "string"
}
}
},
"resolved_nodes": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"name"
],
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"score": {
"type": "number"
}
}
}
}
}
}
}
},
"meta": {
"type": "object",
"required": [
"tenant_plan",
"workspace_id",
"workspace_name",
"timestamp"
],
"properties": {
"persona": {
"type": "string"
},
"timestamp": {
"type": "string"
},
"tenant_plan": {
"enum": [
"free",
"pro",
"enterprise"
],
"type": "string"
},
"workspace_id": {
"type": "string"
},
"gates_applied": {
"type": "array",
"items": {
"type": "string"
}
},
"scoring_model": {
"type": "string"
},
"workspace_name": {
"type": "string"
},
"contract_version": {
"type": "string"
}
}
}
}
},
"annotations": {
"category": "query",
"readOnlyHint": true,
"strict_output": true,
"destructiveHint": false,
"supports_cursor": true,
"supports_idempotency": false,
"requires_confirmation": false,
"supports_since_checkpoint": false
}
}Diagnose Atisbo, including "I connected a source and nothing appeared", "I sent text and no opportunity formed", or "my data is missing". Checks integrations, ingestion, clustering, gates, key scope and migrations, then returns a playbook. share_report files only diagnostics + your text. Use atisbo_lookup/atisbo_analyze for backlog.
| Parameter | Type | Description |
|---|---|---|
| area | string | Narrows the checks. Omit when unsure. |
| problem * | string | What went wrong, in your words. No customer feedback, docs or credentials — the string IS filed in reports. |
| share_report | boolean | File a verdict-only report when the fault is not caller-side; false = diagnose. |
| observed_error | string | The failing error VERBATIM — usually the only evidence. |
{
"name": "atisbo_support",
"title": "Support: diagnose the workspace and MCP itself",
"description": "Diagnose Atisbo, including \"I connected a source and nothing appeared\", \"I sent text and no opportunity formed\", or \"my data is missing\". Checks integrations, ingestion, clustering, gates, key scope and migrations, then returns a playbook. share_report files only diagnostics + your text. Use atisbo_lookup/atisbo_analyze for backlog.",
"inputSchema": {
"type": "object",
"required": [
"problem"
],
"properties": {
"area": {
"enum": [
"ingestion",
"integrations",
"clustering",
"mcp",
"workspace",
"billing",
"unknown"
],
"type": "string",
"description": "Narrows the checks. Omit when unsure."
},
"problem": {
"type": "string",
"maxLength": 2000,
"minLength": 10,
"description": "What went wrong, in your words. No customer feedback, docs or credentials — the string IS filed in reports."
},
"share_report": {
"type": "boolean",
"description": "File a verdict-only report when the fault is not caller-side; false = diagnose."
},
"observed_error": {
"type": "string",
"maxLength": 1000,
"description": "The failing error VERBATIM — usually the only evidence."
}
}
},
"outputSchema": {
"type": "object",
"required": [
"data",
"meta"
],
"properties": {
"data": {
"type": "object",
"required": [
"outcome",
"headline",
"explanation",
"findings",
"next_steps",
"reported"
],
"properties": {
"outcome": {
"enum": [
"resolved",
"answer",
"known_issue",
"captured"
],
"type": "string"
},
"findings": {
"type": "array",
"items": {
"type": "object",
"required": [
"check",
"status",
"facts",
"detail"
],
"properties": {
"check": {
"type": "string"
},
"facts": {
"type": "object",
"properties": {}
},
"detail": {
"type": "string"
},
"status": {
"enum": [
"ok",
"warn",
"fail",
"skipped"
],
"type": "string"
},
"playbook": {
"type": "string"
}
}
}
},
"headline": {
"type": "string"
},
"reported": {
"type": "boolean"
},
"report_id": {
"type": "string"
},
"next_steps": {
"type": "array",
"items": {
"type": "string"
}
},
"explanation": {
"type": "string"
},
"known_issue": {
"type": "object",
"required": [
"claim_id",
"title",
"status",
"affected_report_count"
],
"properties": {
"title": {
"type": "string"
},
"status": {
"type": "string"
},
"claim_id": {
"type": "string"
},
"affected_report_count": {
"type": "number"
}
}
}
}
},
"meta": {
"type": "object",
"required": [
"tenant_plan",
"workspace_id",
"workspace_name",
"timestamp"
],
"properties": {
"persona": {
"type": "string"
},
"timestamp": {
"type": "string"
},
"tenant_plan": {
"enum": [
"free",
"pro",
"enterprise"
],
"type": "string"
},
"workspace_id": {
"type": "string"
},
"gates_applied": {
"type": "array",
"items": {
"type": "string"
}
},
"scoring_model": {
"type": "string"
},
"workspace_name": {
"type": "string"
},
"contract_version": {
"type": "string"
}
}
}
}
},
"annotations": {
"category": "query",
"readOnlyHint": true,
"strict_output": true,
"destructiveHint": false,
"supports_cursor": false,
"supports_idempotency": false,
"requires_confirmation": false,
"supports_since_checkpoint": false
}
}Atisbo is one ordered list of what to do next for a product team — evidence comes in, groups into problems, and is ranked by how much there is and how urgent it sounds. Start with atisbo_orient mode=snapshot, read with atisbo_lookup, file evidence with atisbo_capture, and record decisions with atisbo_decide. To find anything about a topic, call atisbo_lookup mode=claims query="<topic>" (add claim_state=open for untouched work, or focus=all for everything); mode=solutions and mode=knowledge take query= too. To pick up work, call atisbo_lookup mode=work_queue view=executable (what you can finish now); view=needs_pm lists everything waiting on a person, one row per ask. Discovery methods answer without a credential; every tools/call requires a workspace-scoped API key from Settings → Account → Connect agents. A mode's usage notes arrive in meta.guidance the first time you use it in a session, and again with any validation error — keep them. Tool schemas are snapshotted when your session starts: modes added after that stay unknown until you restart the session. If a mode you need errors as unknown, don't retry blindly — compare meta.contract_hash from atisbo_orient mode=snapshot against your Mcp-Session-Id and report the gap. If every call to a tool fails with a client-side error like "Structured content does not match the tool's output schema", or a value you know is published gets rejected as invalid, your cached tools/list is stale: compare the mcp-registry-revision response header against the value you saw at initialize — if it changed, re-initialize the session and refetch tools/list; if it is unchanged, report the gap.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.