prospectapis-mcp
OfficialSummary: This MCP server gives an AI agent tools to search venture funding data, order cited company research briefs, and set up webhook alerts on new funding matches (note: the README's email-verification tools are not present in this server schema).
Search funding rounds (
funding_search) by date range, round stage, amount range, company name, domain, investor and country; newest first, paginated with a cursor.Fetch a single funding record (
funding_get) by id, e.g. to read the full detail behind a search hit.Order a research brief (
research_submit) on a company or person (domain, URL, name, email or LinkedIn URL) with optional product context and purpose (account_research,pre_call,outreach).Poll research results (
research_get) until the brief iscompletedorfailed.Create funding-signal alerts (
watchlist_create) that POST new matching funding events to an HTTPS webhook, signed with a secret.Manage alerts with
watchlist_list,watchlist_get,watchlist_deliveries(last 50 delivery outcomes),watchlist_test(send a signed sample event) andwatchlist_delete.Check the account balance (
account_balance) and remaining free records before large searches.Get live pricing (
pricing_get) and API version (api_version) without an API key.Send feedback or bug reports (
feedback_send) to the vendor team, rate-limited to 10 per hour.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@prospectapis-mcp commission a research brief on stripe.com for pre-call prep"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
prospectapis-mcp
prospectapis-mcp is the MCP server for ProspectAPIs (https://prospectapis.com), for sales and prospecting teams and the AI agents they run in Claude Code, Claude Desktop, Cursor and other MCP clients. It gives your agent twenty-five tools over the ProspectAPIs API: search funding rounds by date, round, amount, company, investor and country, get new matching rounds pushed to your webhook, verify, find and bulk-check email addresses, report what bounced, and order a cited research brief on any company or person. Funding records carry the public announcement URL when there is one. Every account starts with a free $1 balance and no card: records cost $0.02, an email check $0.004 and a completed brief $0.15, with no seats and no subscription. It needs Node.js 22 or later.
Install (Claude Code): claude mcp add prospectapis -e PROSPECTAPIS_API_KEY=pa_live_... -- npx -y prospectapis-mcp
Other clients: run npx -y prospectapis-mcp with PROSPECTAPIS_API_KEY from https://prospectapis.com
Website: https://prospectapis.com/mcp
Tool | Endpoint | Cost |
|
| $0.02 per record returned; no match is free |
|
| $0.02 when found; a missing id is free |
|
| one research at |
|
| free; poll until |
|
| $0.004 per |
|
| free |
|
| free; 1 to 100 outcomes a call |
|
| free to start; $0.004 per |
|
| free |
|
| free; 1,000 a page |
|
| free to manage; a delivered event costs one record, only when your webhook answers 2xx |
|
| free |
|
| free; reports a bug, wrong field or missing capability to the team (10 an hour per key) |
|
| free, no key needed; the live price list |
|
| free, no key needed |
funding_search filters: since, until (YYYY-MM-DD), round (comma list such as seed,series_a),
min_amount_usd, max_amount_usd, company, domain, investor, country, limit (1 to 100) and
cursor (the previous page's next_cursor, passed back unchanged).
research_submit takes exactly one prospect identifier (domain, website_url, company_name,
company_linkedin_url, a work email or linkedin_url), or person_name with company_name, plus an optional
context (your own product, at most 1,000 characters) and purpose (account_research, pre_call or
outreach). It returns a research_id at once; a brief takes 20 to 90 seconds.
email_verify takes emails, a list of 1 to 25 addresses. Each result has status (valid, invalid,
catch-all or unknown), reason, reason_text, score (0 to 100), recommendation (send, send_with_caution, retry_later or do_not_send), charged, flags, smtp_code and catch_all_tier. If the balance covers only
some addresses, the rest come back unknown with reason not_checked_insufficient_credits and are not charged.
Configure
Variable | Required | Default |
| yes (all tools except | none |
| no |
|
Client config (for example claude_desktop_config.json):
{
"mcpServers": {
"prospectapis": {
"command": "npx",
"args": ["-y", "prospectapis-mcp"],
"env": { "PROSPECTAPIS_API_KEY": "pa_live_..." }
}
}
}Claude Code: claude mcp add prospectapis -e PROSPECTAPIS_API_KEY=pa_live_... -- npx -y prospectapis-mcp.
Related MCP server: Nexus Intelligence MCP
FAQ
Where does the funding data come from? Records carry the public announcement URL when there is one.
What is free? A $1 balance when you sign up (about 50 funding records, 250 email checks or 6 research briefs), any search that matches nothing, catch-all and unknown email results, watchlist management, and the balance, pricing and version tools.
Which clients work? Claude Code, Claude Desktop, Cursor and any client that reads an mcpServers config, through npx -y prospectapis-mcp.
Develop
cd mcp
npm install
npm test # mocked fetch over an in-memory MCP transport, no network
npm run checkThe package is versioned independently of the API (SemVer, CHANGELOG.md in this folder). It is marked
private so it cannot be published by accident; publishing is done only from the product's own npm identity.
Available Tools
14 toolsaccount_balanceARead-onlyInspect
Your credit balance and the free records left this month. Free. Check it before a large paged search.
Inputs: no named parameters.
api_versionARead-onlyInspect
The API's version and deployed build. Free, needs no key.
Inputs: no named parameters.
feedback_sendAInspect
Report a bug, a wrong or empty field, a missing capability or a question about ProspectAPIs to the team. Free; limited to 10 delivered reports an hour per account (a 429 means wait, do not retry in a loop). Before reporting that a field is wrong or a parameter is ignored, re-run the call with a value that could only match if it were honoured. Put the exact call, what came back and what you expected in details; never include secrets or API keys. Send only when the user agrees.
Inputs: title (required), details (required), kind, tool.
funding_getARead-onlyInspect
Read one funding record by id. Costs $0.02 when found (free records are used first); a missing id is free.
Inputs: id (required).
funding_searchARead-onlyInspect
Search funding rounds (venture rounds, debt, grants, IPOs), newest announcement first. Costs $0.02 per record returned, after 100 free records a month; a search that matches nothing is free. Page with cursor: pass back next_cursor exactly as returned; a null next_cursor means there are no more matches. Narrow with filters before raising limit.
Inputs: limit, round, since, until, +7 more.
pricing_getARead-onlyInspect
The live price list: funding records (price per record and free records a month), research (whether it is available and its price per brief) and watchlist deliveries. Free, needs no key. Use it to quote a cost before a large call.
Inputs: no named parameters.
research_getARead-onlyInspect
Read a research job by the research_id research_submit returned: status (queued, running, completed, failed), input, result (the brief, once completed) and error (once failed). Free; only your own account's jobs are visible.
Inputs: id (required).
research_submitAInspect
Start a cited pre-call research brief on one prospect: company, funding, traction, competitors, news, people, risks, regions, plus a fit section when you pass context. Give exactly ONE identifier (domain, website_url, company_name, company_linkedin_url, a work email, or linkedin_url), or person_name together with company_name. Returns research_id at once; the brief takes 20 to 90 seconds, so poll research_get every 10 to 15 seconds until status is completed or failed. Costs one research at the price account_balance reports as research_price_usd, held when you submit, charged only when the brief completes and refunded in full if it fails. Free records do not apply.
Inputs: email, domain, context, purpose, +5 more.
watchlist_createAInspect
Save a funding-signal alert: a set of funding_search filters plus an https webhook. Each NEW funding event that matches is POSTed to the webhook, signed with the returned secret (header Prospect-Signature: t=..,v1=HMAC-SHA256). Creating is free; each delivered event costs one record ($0.02, free records first), charged only when the webhook answers 2xx. The secret is shown once. Max 20 active per account.
Inputs: name (required), filters (required), webhook_url (required).
watchlist_deleteBInspect
Delete a funding-signal alert and its delivery history. Free.
Inputs: id (required).
watchlist_deliveriesARead-onlyInspect
The last 50 deliveries of one alert and their outcome (delivered, retry, failed, no_credit). Free.
Inputs: id (required).
watchlist_getARead-onlyInspect
One funding-signal alert: its name, filters, webhook URL, whether it is active and why it was paused (never its secret). Free.
Inputs: id (required).
watchlist_listCRead-onlyInspect
Your funding-signal alerts (without their secrets). Free.
Inputs: no named parameters.
watchlist_testAInspect
Send a signed sample event to the alert's webhook now, to build and verify the receiver. Free; 5 a minute.
Inputs: id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Each tool targets a distinct resource-action: funding_search vs funding_get, research_submit vs research_get, and the watchlist family splits cleanly into create/list/get/deliveries/test/delete. The supporting utilities (account_balance, feedback_send, pricing_get, api_version) are all clearly differentiated. The only faint overlap is pricing_get vs account_balance, but one quotes prices while the other reports the caller's balance, so confusion risk is minimal.
All 14 names use lowercase snake_case with a consistent resource_action pattern (funding_search, research_submit, watchlist_create, account_balance, feedback_send). No camelCase or mixed verb styles appear. Grouping by resource prefix (funding_, research_, watchlist_) further reinforces predictability.
14 tools is well-scoped for a server covering three functional areas (funding data, cited research, and webhook alerts) plus billing/info utilities. Each tool earns its place and none look redundant. This sits comfortably in the ideal 3-15 range.
The surface covers the core lifecycle: funding search+retrieve, research submit+poll, full watchlist CRUD plus deliveries and test, and account/pricing/version utilities. Minor gaps exist—there is no watchlist_update (alerts must be deleted and recreated to change filters) and no research_delete/cancel—but these are workaroundable and don't block main workflows.
Maintenance
Related MCP Connectors
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
AI research on companies and industries — one MCP tool per research domain.
16 Bitcoin, business, data, text, and developer tools for AI agents over one MCP endpoint.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceConnects Claude or any MCP-compatible AI to a database of 960+ active VC funds for searching, fund profiles, live GP signals, and AI-powered startup-investor matching.1-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to perform company due diligence, OSINT, competitive, SEO, market, finance and regulatory research through a single MCP endpoint exposing 45 tools that draw on official public APIs, local D1 mirrors, and optional self-hosted sidecars. Every response is labelled by evidence class, so inferred estimates are never presented as equivalent to official data.6 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query live pricing, resale, company KYC, SEC filings, patents, trademarks, public tenders, auctions and related market intelligence through MCP, returning clean typed JSON from primary sources on a pay-per-result basis.MIT
- AlicenseNot gradedqualityBmaintenanceExposes twelve tools (fourteen with company requests enabled) that let agents search and read verified funding rounds, company funding histories with total raised, investor profiles and rankings, and the news behind each record. Filters cover stage, sector, amount, certainty, and date windows.10MIT