{
  "markdown": "<!-- mcp-name: io.github.adamhudson777/filingrail-mcp -->\n\n# filingrail-mcp — SEC EDGAR filings inside Claude, Cursor, and any MCP agent\n\nGive your AI agent live SEC EDGAR data: company financials, insider trades, 8-K events, 13F holdings, and the raw filings stream — all normalized to clean JSON, every number traceable back to its `sec.gov` source filing.\n\nOne `pip install`, one API key, and your agent can answer *\"What was Apple's cash position last quarter?\"* or *\"List Berkshire Hathaway's top 10 holdings as of 2026-Q1\"* — against real filings, not its training data.\n\n```bash\npip install filingrail-mcp\n```\n\n> **Live on PyPI:** [pypi.org/project/filingrail-mcp](https://pypi.org/project/filingrail-mcp/) · MIT licensed · Python 3.10+\n\n## Why this exists\n\nEvery number a public company reports to the SEC is free and open on EDGAR. The bottleneck isn't access — it's the XBRL parser, the tag-drift normalizer, the rate-limit governor, and the dedup layer you'd have to write before you get the one figure you actually wanted. `filingrail-mcp` hands your agent the finished JSON instead.\n\n- **Source-traceable.** Every financial response carries the originating `source_filing_url`. Click it, see the exact 10-K / 10-Q on sec.gov. No \"trust us.\"\n- **Normalized.** `revenue` is `revenue`, whether the filer tagged it `us-gaap:Revenues`, `SalesRevenueNet`, or `RevenueFromContractWithCustomerExcludingAssessedTax`. 1.8M+ XBRL rows back to 2006.\n- **Zero plumbing.** No EDGAR User-Agent config, no local parser, no rate-limit governor. The API handles all of it.\n\n## Get a key (free tier, no card)\n\nFilingrail is a REST API on RapidAPI. The free tier is **50 calls/day, no credit card**:\n\n**→ [Subscribe to Filingrail on RapidAPI](https://rapidapi.com/hudson-enterprises-llc-hudson-enterprises-llc-default/api/filingrail)** and copy your `X-RapidAPI-Key`.\n\nThe end user brings their own key — set it as `RAPIDAPI_KEY` in your MCP client config (below).\n\n## Configure your agent\n\n### Claude Desktop\n\nEdit `%APPDATA%/Claude/claude_desktop_config.json` (Windows) or `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS):\n\n```json\n{\n  \"mcpServers\": {\n    \"filingrail\": {\n      \"command\": \"filingrail-mcp\",\n      \"env\": { \"RAPIDAPI_KEY\": \"your-rapidapi-key-here\" }\n    }\n  }\n}\n```\n\nRestart Claude Desktop. The Filingrail tools (`search_companies`, `get_financials`, `get_insider_trades`, …) appear in the tool list. Then just ask a question in plain English.\n\n### Cursor / Continue / any other MCP client\n\nPoint the client at `filingrail-mcp` as the stdio command and pass `RAPIDAPI_KEY` as an environment variable. Same shape as above.\n\nIf your client only accepts a raw command, use:\n\n```json\n{ \"command\": \"filingrail-mcp\", \"env\": { \"RAPIDAPI_KEY\": \"your-rapidapi-key-here\" } }\n```\n\n## Tools exposed\n\n| Tool | What it does |\n|---|---|\n| `search_companies(q, limit)` | Resolve ticker / CIK / name fragment to a company (8,000+ SEC issuers, fuzzy match) |\n| `get_recent_filings(form_type, cik, limit)` | Recent filings firehose — filter by form (`10-K`, `8-K`, `4`, `13F-HR`) or CIK |\n| `get_financials(ticker_or_cik, limit)` | Latest 10-K / 10-Q normalized line items + `source_filing_url` |\n| `get_financials_history(ticker_or_cik, period, limit, …)` | Historical quarterly or annual series |\n| `get_insider_trades(ticker_or_cik, since, limit)` | Form 4 transactions — who bought/sold, when, how much |\n| `get_8k_events(ticker_or_cik, since, limit)` | 8-K material events with SEC item codes (5.02, 2.01, …) |\n| `get_13f_holdings(institution_cik, quarter, limit)` | Institutional holdings (e.g. Berkshire = CIK 1067983) |\n| `health()` | API liveness check |\n\n## Try it\n\nAfter installing and configuring, ask your agent:\n\n- *\"What was Apple's revenue and operating income last quarter, and link me the filing.\"*\n- *\"Show me insider sells at NVIDIA in the last 30 days.\"*\n- *\"What 8-K events did Tesla file this month?\"*\n- *\"List Berkshire Hathaway's 10 largest 13F positions for 2026-Q1.\"*\n\n## What it is not\n\nHonest caveats:\n\n- **Not real-time.** New filings appear within ~24h of EDGAR acceptance (fair-access policy).\n- **Not Bloomberg.** No intraday prices, options chains, non-US issuers, or analyst estimates.\n- **Structured SEC data, traced to source** — that's the whole product.\n\n## Pricing\n\n| Tier | Price | Calls/month |\n|---|---|---|\n| Free | $0 | 1,500 (50/day) |\n| Pro | $9/mo | 5,000 |\n| Ultra | $49/mo | 50,000 |\n| Mega | $199/mo | 500,000 |\n\nKeys and billing are handled by RapidAPI. **[Get yours →](https://rapidapi.com/hudson-enterprises-llc-hudson-enterprises-llc-default/api/filingrail)**\n\n## Links\n\n- [Get an API key (RapidAPI listing)](https://rapidapi.com/hudson-enterprises-llc-hudson-enterprises-llc-default/api/filingrail)\n- [Filingrail homepage](https://filingrail.hudsonenterprisesllc.com)\n- [Python SDK (sync + async)](https://pypi.org/project/filingrail/) — `pip install filingrail`\n- [API status page](https://status.hudsonenterprisesllc.com)\n- Questions / issues: `support@hudsonenterprisesllc.com`\n\n## License\n\nMIT © Hudson Enterprises LLC\n",
  "bytes": 5095,
  "sha": "68eb099be055e6c2b1f3fa77fe89caae0e417319a6bae3649d6f1def6328f9ee",
  "repo_slug": "adamhudson777/filingrail-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_adamhudson777_filingrail_mcp_46bad0aa/readme"
}