
Filingrail Mcp
io.github.adamhudson777Published by GitHub account adamhudson777v0.1.3Updated Oct 24, 2026
SEC EDGAR financials, insider trades, 8-K events, and 13F holdings as MCP tools.
Overview
Local MCP server that gives an assistant SEC EDGAR data — company financials, insider trades, 8-K events, 13F holdings and recent filings — as normalized JSON.
- What you can do
- Resolve tickers, CIKs or name fragments to SEC issuers with fuzzy matching
- List recent filings filtered by form type or CIK
- Fetch latest and historical 10-K/10-Q financial line items, each with a source filing link
- Retrieve Form 4 insider trades and 8-K material events with SEC item codes
- Look up institutional 13F holdings by quarter
- Check API liveness
- When to use it
- Useful when you want an assistant to answer questions about US public company financials, insider activity, material events or institutional holdings from real filings rather than training data, with every figure traceable to its source filing.
- Requirements
- Runs locally as a Python package (Python 3.10+) installed with pip and launched as a stdio command. Needs a RapidAPI key supplied in the RAPIDAPI_KEY environment variable; a free tier of 50 calls per day is offered. Network access to the Filingrail API is required.
Installation
In SourceWeft
- Open Filingrail Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
filingrail-mcp — SEC EDGAR filings inside Claude, Cursor, and any MCP agent
Give 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.
One 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.
Live on PyPI: pypi.org/project/filingrail-mcp · MIT licensed · Python 3.10+
Why this exists
Every 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.
- 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." - Normalized.
revenueisrevenue, whether the filer tagged itus-gaap:Revenues,SalesRevenueNet, orRevenueFromContractWithCustomerExcludingAssessedTax. 1.8M+ XBRL rows back to 2006. - Zero plumbing. No EDGAR User-Agent config, no local parser, no rate-limit governor. The API handles all of it.
Get a key (free tier, no card)
Filingrail is a REST API on RapidAPI. The free tier is 50 calls/day, no credit card:
→ Subscribe to Filingrail on RapidAPI and copy your X-RapidAPI-Key.
The end user brings their own key — set it as RAPIDAPI_KEY in your MCP client config (below).
Configure your agent
Claude Desktop
Edit %APPDATA%/Claude/claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
Restart 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.
Cursor / Continue / any other MCP client
Point the client at filingrail-mcp as the stdio command and pass RAPIDAPI_KEY as an environment variable. Same shape as above.
If your client only accepts a raw command, use:
Tools exposed
Try it
After installing and configuring, ask your agent:
- "What was Apple's revenue and operating income last quarter, and link me the filing."
- "Show me insider sells at NVIDIA in the last 30 days."
- "What 8-K events did Tesla file this month?"
- "List Berkshire Hathaway's 10 largest 13F positions for 2026-Q1."
What it is not
Honest caveats:
- Not real-time. New filings appear within ~24h of EDGAR acceptance (fair-access policy).
- Not Bloomberg. No intraday prices, options chains, non-US issuers, or analyst estimates.
- Structured SEC data, traced to source — that's the whole product.
Pricing
Keys and billing are handled by RapidAPI. Get yours →
Links
- Get an API key (RapidAPI listing)
- Filingrail homepage
- Python SDK (sync + async) —
pip install filingrail - API status page
- Questions / issues:
[email protected]
License
MIT © Hudson Enterprises LLC
Source: README.md at commit b4cd77d
Tools
0Version history
2- v0.1.3LatestOct 8, 2026
- v0.1.2Sep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts