Fundz Agent API is an MCP server published by net.fundz, hosted at api.fundz.net. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including events_for_icp, predicted_next, watchlist_diff, why_now.
Dated funding and SEC 8-K events, each linked to the filing it came from.
3 connections through 5 shared values. Tap any node.
Find companies matching an ideal-customer profile that have had recent funding or SEC 8-K events, ranked, each with its evidence. Use this to build a list from scratch. `min_signals` filters for companies with several signals at once. Costs 1 unit.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Rows per call. Hard-capped at 100 server-side; values above are clamped, not refused. Page with `cursor` for more. |
| cursor | string | |
| states | array | Full state names as stored, e.g. 'California'. |
| industries | array | |
| min_signals | integer |
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.
Inferred from the host name and headers: what a server runs on, not who runs it.
| lookback_days | integer |
| max_employees | integer |
| min_employees | integer |
{
"name": "events_for_icp",
"title": "Ranked companies matching an ICP, each with evidence",
"description": "Find companies matching an ideal-customer profile that have had recent funding or SEC 8-K events, ranked, each with its evidence. Use this to build a list from scratch. `min_signals` filters for companies with several signals at once. Costs 1 unit.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 25,
"maximum": 100,
"description": "Rows per call. Hard-capped at 100 server-side; values above are clamped, not refused. Page with `cursor` for more."
},
"cursor": {
"type": "string"
},
"states": {
"type": "array",
"items": {
"type": "string"
},
"description": "Full state names as stored, e.g. 'California'."
},
"industries": {
"type": "array",
"items": {
"type": "string"
}
},
"min_signals": {
"type": "integer",
"default": 1
},
"lookback_days": {
"type": "integer",
"default": 90
},
"max_employees": {
"type": "integer"
},
"min_employees": {
"type": "integer"
}
}
},
"annotations": {
"title": "Ranked companies matching an ICP, each with evidence",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}EXPERIMENTAL forecast of what a company may do next (raise, be acquired, acquire), from FundzScore v3. Treat `lift` as a ranking aid only: `base_rate` is a population mean rather than a validated historical rate, and the forward cohorts do not resolve until 2026-10-22 and 2027-02-19. Do not present these as predictions to an end user. Costs 1 unit.
| Parameter | Type | Description |
|---|---|---|
| domain | string | |
| org_id | integer |
{
"name": "predicted_next",
"title": "FundzScore v3 forecasts (experimental)",
"description": "EXPERIMENTAL forecast of what a company may do next (raise, be acquired, acquire), from FundzScore v3. Treat `lift` as a ranking aid only: `base_rate` is a population mean rather than a validated historical rate, and the forward cohorts do not resolve until 2026-10-22 and 2027-02-19. Do not present these as predictions to an end user. Costs 1 unit.",
"inputSchema": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"org_id": {
"type": "integer"
}
}
},
"annotations": {
"title": "FundzScore v3 forecasts (experimental)",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Given a book of up to 400 company domains and a cursor, return ONLY those with new evidence since that cursor. This is the tool to poll daily or weekly rather than re-fetching every company. Costs 0.1 units per company CHECKED — not per company returned — so a quiet week still reflects the work done. Split a larger book across several calls: the request body is capped at 8 KB at the edge, and because pricing is per company checked, two calls of 200 cost exactly what one call of 400 would.
| Parameter | Type | Description |
|---|---|---|
| since | string | The `next_cursor` from your previous call. |
| domains * | array |
{
"name": "watchlist_diff",
"title": "Only the companies in your book with new events since a cursor",
"description": "Given a book of up to 400 company domains and a cursor, return ONLY those with new evidence since that cursor. This is the tool to poll daily or weekly rather than re-fetching every company. Costs 0.1 units per company CHECKED — not per company returned — so a quiet week still reflects the work done. Split a larger book across several calls: the request body is capped at 8 KB at the edge, and because pricing is per company checked, two calls of 200 cost exactly what one call of 400 would.",
"inputSchema": {
"type": "object",
"required": [
"domains"
],
"properties": {
"since": {
"type": "string",
"format": "date",
"description": "The `next_cursor` from your previous call."
},
"domains": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 400
}
}
},
"annotations": {
"title": "Only the companies in your book with new events since a cursor",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Why to contact ONE company right now: dated funding and SEC 8-K evidence, each item linking to its source filing or announcement. Use this when you have a company and need the reason and the proof. Costs 1 unit. `evidence` covers the last `lookback_days` days (default 365, max 1825); `last_event` is ALWAYS the most recent event on record whatever its age, with `within_lookback` saying whether it also appears in `evidence`. So an empty `evidence` with a populated `last_event` means the company is known and simply quiet — widen `lookback_days` to bring it in. `resolved:false` means we hold no such company at all, which is a different answer again. `resolution_confidence` (0-1) says how strongly the resolved name agrees with the domain asked about; treat anything below 0.67 as unconfirmed attribution.
| Parameter | Type | Description |
|---|---|---|
| domain | string | Any spelling: bare, www., scheme, path. |
| org_id | integer | |
| lookback_days | integer | Window for `evidence[]`, in days. Clamped to 1825. Does not affect `last_event`, which is never age-limited. |
{
"name": "why_now",
"title": "Dated evidence for one company",
"description": "Why to contact ONE company right now: dated funding and SEC 8-K evidence, each item linking to its source filing or announcement. Use this when you have a company and need the reason and the proof. Costs 1 unit. `evidence` covers the last `lookback_days` days (default 365, max 1825); `last_event` is ALWAYS the most recent event on record whatever its age, with `within_lookback` saying whether it also appears in `evidence`. So an empty `evidence` with a populated `last_event` means the company is known and simply quiet — widen `lookback_days` to bring it in. `resolved:false` means we hold no such company at all, which is a different answer again. `resolution_confidence` (0-1) says how strongly the resolved name agrees with the domain asked about; treat anything below 0.67 as unconfirmed attribution.",
"inputSchema": {
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Any spelling: bare, www., scheme, path."
},
"org_id": {
"type": "integer"
},
"lookback_days": {
"type": "integer",
"default": 365,
"maximum": 1825,
"minimum": 1,
"description": "Window for `evidence[]`, in days. Clamped to 1825. Does not affect `last_event`, which is never age-limited."
}
}
},
"annotations": {
"title": "Dated evidence for one company",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Fundz Agent API: dated funding and SEC 8-K event evidence, each item linking to the filing or announcement it came from. Two lanes only — funding (SEC Form D and announcements) and SEC 8-K; there is no contact or people data. Every evidence item carries a `source_kind` (sec_filing or press_or_news) and a `source_url`; cite it. Calls are metered against the caller's key: why_now, events_for_icp and predicted_next cost 1 unit each, and watchlist_diff costs 0.1 per company CHECKED — so poll a book with watchlist_diff and a cursor rather than calling why_now across it. predicted_next is EXPERIMENTAL: treat `lift` as a ranking aid, never as a validated probability, and do not present it to an end user as a prediction.
Names, descriptions and schemas were written by the server and are shown as data.