Fundz Agent API のリモート MCP サーバーとは何ですか?
Fundz Agent API のリモート MCP サーバーは、https://api.fundz.net/v1/agent/mcp にホストされた Model Context Protocol エンドポイントです。AI アシスタントはローカルに何もインストール・実行することなく接続できます。
@Fundz LLC
基本情報
Fundz gives an agent the reason to reach out and the proof behind it. Four tools: why_now returns one company's dated evidence, each item linking to the SEC filing or announcement it came from. events_for_icp finds companies matching a profile that have had recent events. watchlist_diff takes a book of up to 400 domains and a cursor and returns only what moved, which is the endpoint to poll. predicted_next is an experimental forecast and is labelled as such. Every evidence item carries source_kind, either sec_filing or press_or_news — we label which rather than describing the whole corpus as primary-filed, because only part of the funding lane is a filing. Coverage is funding (SEC Form D and announcements) and SEC 8-K. No contact or people data. When there is no event in your window it returns an empty answer rather than inventing a reason to call. Metered: one unit per call, 0.1 per company checked by watchlist_diff.
https://api.fundz.net/v1/agent/mcpclaude mcp add fundz-agent-api --transport http https://api.fundz.net/v1/agent/mcp --header "X-Fundz-Key: YOUR_KEY"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.
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.
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.
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.
Dated funding rounds and SEC 8-K events for companies, with every item linked to the filing or announcement it came from. It gives an agent the reason to reach out and the proof behind it, so a rep can open the source before anything is sent.
Send your key in an X-Fundz-Key header. Authorization: Bearer and X-Api-Key also work. Discovery is keyless: initialize and tools/list need no credential, so a client can inspect the server before you hand one over. Only tools/call requires a key.
why_now — one company's dated evidence, each item linking to its source. 1 unit.events_for_icp — companies matching an ideal-customer profile that have had recent events. 1 unit.watchlist_diff — only the companies in your book with new evidence since a cursor. 0.1 units per company checked, up to 400 domains per request.predicted_next — EXPERIMENTAL forecast. Treat lift as a ranking aid, not a validated rate. 1 unit.Funding (SEC Form D parsed from EDGAR, plus announcements) and SEC 8-K. Every evidence item carries source_kind, either sec_filing or press_or_news — we label which rather than describing the whole corpus as primary-filed, because only part of the funding lane is a filing.
No contact or people data. No hiring signals. When there is no event in your window it returns an empty answer rather than inventing a reason to call, and last_event tells you when the most recent one actually was.
Metered at $0.06 per unit with a $25/month minimum. Flat Platform tiers at 50k / 150k / 400k units.
Fundz Agent API のリモート MCP サーバーは、https://api.fundz.net/v1/agent/mcp にホストされた Model Context Protocol エンドポイントです。AI アシスタントはローカルに何もインストール・実行することなく接続できます。
エンドポイント https://api.fundz.net/v1/agent/mcp を Claude Code、Cursor、VS Code など任意の MCP 対応クライアントに追加してください。このページのセットアップ手順で各クライアントを一度に設定できます。
はい。Fundz Agent API は API キーが必要です——取得方法は公式ドキュメントを確認し、クライアントの設定に追加してください。
Fundz Agent API は Streamable HTTP エンドポイントを公開しており、これはリモート MCP サーバーで広く使われ、主要な MCP クライアントがサポートするトランスポートです。
Production remote MCP server with 35 safe web-intelligence tools: 32 paid x402 URL operations plus 3 free discovery/demo tools. Base Mainnet USDC, no account or API key; SSRF protection, strict schemas and idempotent set
Marketing campaign and audience insights from Adobe
One MCP connection for all your Gmail, Google Calendar, Drive and Contacts accounts, Slack workspaces and Notion — free.
Search and read current AWS documentation, check regional availability and load AWS agent skills, with no AWS account needed.
Remote MCP server that turns Claude, ChatGPT, or Cursor into a full ad workflow: research any brand's live Facebook and TikTok ads, clone the proven winners for your own brand, and launch real campaigns on Google, TikTok
コメント