An MCP server for querying U.S. SEC EDGAR public filings and issuer data. It can resolve companies, search and list filings, inspect offering documents, fetch filing text, and retrieve company facts and insider trading information.
From the registry: SEC EDGAR filings (10-K, 10-Q, 8-K), XBRL financials, and full-text filing search. No API key.
Please install the `edgar-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.12+** — Python 3.12 or newer is required to run the server.
- **Install uv** — The recommended zero-clone install path uses uvx from the uv tool. (https://docs.astral.sh/uv/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["mcpwright-edgar"]
- required environment variables:
- `EDGAR_MCP_USER_AGENT`: Descriptive User-Agent with contact info sent to the SEC. The README says the SEC requires this for fair access and shows it in client examples. (example: `<your-app> <[email protected]>`)
- optional environment variables:
- `EDGAR_MCP_CACHE`: Set to 0 to disable the server's in-memory cache. (example: `0`)
Note: The server runs locally over stdio. No API key is required because it uses public SEC endpoints. The README notes hosted chat connectors expect a remote HTTP MCP server, but this package itself is a local stdio server.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.EDGAR_MCP_USER_AGENTrequiredDescriptive User-Agent string with contact info sent to the SEC with requests.EDGAR_MCP_CACHESet to 0 to disable in-memory caching.MCP server for searching Airweave collections with natural language queries.