io.github.bch1212由 GitHub 帳號 bch1212 發布v0.1.0更新於 Oct 26, 2026
US public-records intelligence for AI agents — companies, SEC, courts, spending, licenses.
面向美國公開紀錄調查的遠端 MCP 伺服器：公司登記資料、SEC 文件、聯邦法院案件、聯邦支出、執照與補助機會。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.bch1212%2Fpubrecords/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"pubrecords": {
"type": "http",
"url": "https://mcp-pubrecords-production.up.railway.app/mcp/",
"headers": {
"X-API-Key": "<YOUR_API_KEY>"
}
}
}
}One paid MCP server for US public records, federal grants, and federal contracts. Companies, SEC filings, court dockets, spending awards, licenses, Grants.gov opportunities, and SAM.gov contract notices share a single API key and a single bill.
This repository is the combined Halverson IQ Data server.
Not part of this server: business-intel and outdoor datasets (separate or retired), and web-page fetching (a different pipeline with its own fetchers and cache).
One customer key is checked on every tool. Free tier is 30 calls/day across the whole server. Pro is unlimited on the same key. Upgrade: https://mcpize.com/pubrecords-mcp
Keys are issued per user. Ask the operator for a key, or have them mint one with POST /admin/keys. Examples below use the placeholder YOUR_API_KEY.
focus_areas on the REST route is a comma-separated string. The MCP tool accepts a list.
Contract tools call SAM.gov only when SAM_API_KEY is set. If it is missing they return {"success": false, "error": "SAM_API_KEY is not configured"} and do not send a request.
Note the trailing slash on
/mcp/. Without it the gateway issues a 307 that drops the POST body, breaking the JSON-RPC handshake.
Then set the API key in your client:
A thin Python wrapper for non-MCP integrations lives in pubrecords-sdk/:
Every MCP tool is also available over plain HTTP. Send the same X-API-Key on each call.
Production URL: https://mcp-pubrecords-production.up.railway.app
GET /usage returns the remaining daily quota for that key. GET /health is unauthenticated.
POST /admin/keys and POST /billing/upgrade return 403 unless PUBRECORDS_ADMIN_TOKEN is set and the X-Admin-Token header matches it. There is no default admin token.
Promote that same key to the paid tier (this is the single billing switch):
Run tests:
Environment variables (see .env.example):
Responses are cached for 24 hours by default.
For fresher queries, set PUBRECORDS_CACHE_TTL=300 (5 minutes). That multiplies upstream traffic.
The server returns a structured error envelope instead of invented rows when a query is outside coverage.
get_ucc_filings returns {"error": "not_implemented"} until per-state adapters land.OPENCORPORATES_TOKEN for production.form_type.SAM_API_KEY is set in the environment. Apply at https://sam.gov. The key is not embedded in this repo.search_awards reads Award Notice rows from the opportunities API. Deeper recipient rollups stay on lookup_federal_spending (USASpending).match_opportunities is deterministic token overlap on title and agency. It does not call a model.This server proxies and caches public records that are already free to access from federal and public sources. Cached payloads are kept for 24 hours and can be flushed by deleting the SQLite file. Customer API keys and the admin token belong in the environment and the SQLite key store. Do not commit them.
來源：README.md，提交 fee4b77
Search US business entities by name (OpenCorporates). Args: name: Company or trade name to search for. state: 2-letter US state code (e.g. 'CA') to narrow jurisdiction. status: Filter by current status (e.g. 'active', 'dissolved'). limit: Max results (1-100, default 25).
name必填limitstatestatusFetch officers, agent, and filing history for a known company. Args: company_id: OpenCorporates company number. jurisdiction: Jurisdiction code (e.g. 'us_de', 'us_ca').
company_id必填jurisdiction必填Search SEC EDGAR full-text for filings. Args: company_name: Issuer name or keyword. form_type: Filing form (e.g. '10-K', '10-Q', '8-K'). date_from: Earliest filing date (YYYY-MM-DD). limit: Max results (1-100, default 25).
limitdate_fromform_typecompany_name必填Fetch metadata + index URL for one SEC filing by accession number. Args: accession_number: EDGAR accession number (e.g. '0001193125-21-000001').
accession_number必填Search federal court cases via CourtListener (RECAP). Args: party_name: Plaintiff or defendant name. court: CourtListener court id (e.g. 'nyed', 'txsd'). date_from: Earliest filing date (YYYY-MM-DD). limit: Max results (1-50, default 25).
courtlimitdate_fromparty_name必填Search USASpending.gov for awards (contracts + grants). Args: recipient_name: Award recipient name. agency: Awarding agency name (e.g. 'Department of Defense'). year: Fiscal year (e.g. 2024). limit: Max results (1-100, default 25).
yearlimitagencyrecipient_name必填Look up healthcare providers in the NPPES NPI registry. Args: name: Provider individual or organization name. specialty: Taxonomy description (e.g. 'Internal Medicine'). state: 2-letter state code. limit: Max results (1-200, default 25).
namelimitstatespecialtyUCC lien lookup. (Roadmap; returns not_implemented per state.) Args: debtor_name: Name of the debtor. state: 2-letter state code.
state必填debtor_name必填Cross-reference an entity across multiple sources and score confidence. Args: name: Entity name to verify. state: Optional 2-letter state code for jurisdiction filtering.
name必填stateSearch professional / business licenses (NPI + FCC, more sources roadmap). Args: entity_name: Licensee name. license_type: 'npi' | 'medical' | 'fcc' | 'radio' | 'all'. state: 2-letter state code.
stateentity_name必填license_type已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
claude mcp add --transport http halverson-iq-data https://mcp-pubrecords-production.up.railway.app/mcp/X-API-Key: YOUR_API_KEYpip install pubrecordsfrom pubrecords import PubRecords
client = PubRecords(api_key="YOUR_API_KEY")print(client.health())print(client.search_companies(name="Apple", state="CA"))print(client.search_grants(keyword="broadband"))curl -H "X-API-Key: YOUR_API_KEY" \ "https://mcp-pubrecords-production.up.railway.app/tools/search_companies?name=Apple&state=CA"
curl -H "X-API-Key: YOUR_API_KEY" \ "https://mcp-pubrecords-production.up.railway.app/tools/search_grants?keyword=broadband"GET /health (no auth)GET /usage (X-API-Key)GET /tools/<tool_name>?... (X-API-Key)POST /admin/keys (X-Admin-Token; fails closed)POST /billing/upgrade (X-Admin-Token; fails closed)POST /mcp/ (MCP streamable-http transport)curl -X POST https://mcp-pubrecords-production.up.railway.app/admin/keys \ -H "X-Admin-Token: $PUBRECORDS_ADMIN_TOKEN" \ -H "Content-Type: application/json" \ -d '{"key":"YOUR_API_KEY","tier":"free"}'curl -X POST https://mcp-pubrecords-production.up.railway.app/billing/upgrade \ -H "X-Admin-Token: $PUBRECORDS_ADMIN_TOKEN" \ -H "Content-Type: application/json" \ -d '{"key":"YOUR_API_KEY"}'git clone https://github.com/bch1212/mcp-pubrecords.gitcd mcp-pubrecordspython3 -m venv .venv && source .venv/bin/activatepip install -r requirements.txtcp .env.example .envuvicorn server:app --reload --port 8000pytest -v