PluginBench
MCP Server
Active
AGPL-3.0

io.github.stefanoamorelli/sec-edgar-mcp MCP Server

io.github.stefanoamorelli/sec-edgar-mcp

Access SEC EDGAR filings, financial statements, and insider trading data with exact numeric precision.

What is the io.github.stefanoamorelli/sec-edgar-mcp MCP server?

The SEC EDGAR MCP server provides AI assistants with access to US public company filings through the SEC EDGAR API. It enables retrieval of company information, financial statements (balance sheets, income statements, cash flow), 10-K/10-Q/8-K filings, and insider trading data with XBRL-parsed precision. All responses include SEC filing URLs for verification.

This server connects Claude and other AI assistants to comprehensive US public company financial data. You can look up companies by CIK, retrieve full filings and specific sections, extract parsed financial statements, and access insider trading transactions. It's built on edgartools and provides exact numeric data suitable for financial analysis and research.

How to install io.github.stefanoamorelli/sec-edgar-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • SEC_EDGAR_USER_AGENT
    required

    The user agent to access the SEC EDGAR API

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "sec-edgar-mcp": {
      "command": "uvx",
      "args": [
        "sec-edgar-mcp"
      ],
      "env": {
        "SEC_EDGAR_USER_AGENT": "<YOUR_SEC_EDGAR_USER_AGENT>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • CIK Lookup — Search for companies and retrieve their Central Index Key (CIK) identifier
  • Company Info — Retrieve detailed company information from SEC EDGAR
  • Company Facts — Access company-specific facts and data from SEC filings
  • 10-K Retrieval — Fetch annual report (Form 10-K) filings
  • 10-Q Retrieval — Fetch quarterly report (Form 10-Q) filings
  • 8-K Retrieval — Fetch current report (Form 8-K) filings
  • Section Extraction — Extract specific sections from SEC filings
  • Balance Sheet — Retrieve and parse balance sheet data from XBRL filings
  • Income Statement — Retrieve and parse income statement data from XBRL filings
  • Cash Flow Statement — Retrieve and parse cash flow statement data from XBRL filings
  • Insider Trading — Access Form 3/4/5 insider trading transactions

Use cases

  • Research company financial health by extracting balance sheets, income statements, and cash flow data from annual and quarterly reports
  • Track insider trading activity by retrieving Form 3/4/5 transactions for specific companies
  • Analyze 8-K filings to monitor material events and corporate announcements
  • Compare financial metrics across multiple companies using XBRL-parsed data
  • Build financial analysis tools that pull verified SEC data with exact numeric precision

io.github.stefanoamorelli/sec-edgar-mcp MCP server FAQ

What is the SEC EDGAR MCP server?

It's an MCP server that gives AI assistants access to US public company filings, financial statements, and insider trading data from the SEC EDGAR database. All data is retrieved from official SEC sources with exact numeric precision.

Is this server free to use?

Yes, the server is free and open-source under AGPL-3.0 license. It accesses the public SEC EDGAR API which is free. Commercial licensing is available by contacting stefano@amorelli.tech.

How do I install it in Claude or Cursor?

Install via pip (pip install sec-edgar-mcp), conda, or Docker. Add it to your MCP configuration with the command to run the server. See the documentation at sec-edgar-mcp.amorelli.tech for detailed setup instructions for your platform.

Do I need authentication to use this server?

No authentication is required to access public SEC EDGAR data. However, you should set the SEC_EDGAR_USER_AGENT environment variable with your name and email when running the server.

What financial data can I access?

You can retrieve balance sheets, income statements, cash flow statements (XBRL-parsed), company facts, and all SEC filing types including 10-K (annual), 10-Q (quarterly), and 8-K (current reports).

Can I use this on platforms like Dify?

Yes, the server supports HTTP transport via streamable-http mode (python -m sec_edgar_mcp.server --transport streamable-http --port 9870) for platforms that don't support stdio-based MCP.

README (reference)

Source of truth, from the repository.

SEC EDGAR MCP

<p align="center"> <a href="https://pypi.org/project/sec-edgar-mcp/"><img alt="PyPI" src="https://img.shields.io/pypi/v/sec-edgar-mcp.svg" /></a> <a href="https://anaconda.org/stefanoamorelli/sec-edgar-mcp"><img alt="Conda Version" src="https://img.shields.io/conda/vn/stefanoamorelli/sec-edgar-mcp.svg" /></a> <img alt="Python: 3.11+" src="https://img.shields.io/badge/python-3.11+-brightgreen.svg" /> <img alt="License: AGPL-3.0" src="https://img.shields.io/badge/license-AGPL--3.0-blue.svg" /> <a href="https://mseep.ai/app/0132880c-5e83-410b-a1d5-d3df08ed7b5c"><img alt="Verified on MseeP" src="https://mseep.ai/badge.svg" /></a> <a href="https://doi.org/10.5281/zenodo.17123166"><img alt="DOI" src="https://zenodo.org/badge/DOI/10.5281/zenodo.17123166.svg" /></a> <a href="https://github.com/stefanoamorelli/sec-edgar-mcp/actions/workflows/evals.yml"><img alt="Evals" src="https://github.com/stefanoamorelli/sec-edgar-mcp/actions/workflows/evals.yml/badge.svg" /></a> </p>

MCP server for accessing SEC EDGAR filings. Connects AI assistants to company filings, financial statements, and insider trading data with exact numeric precision.

Built on edgartools.

https://github.com/user-attachments/assets/d310eb42-b3ca-467d-92f7-7d132e6274fe

<details> <summary>See demo video</summary> <a href="https://www.loom.com/share/17fcd7d891fe496f9a6b8fb85ede66bb"> <img style="max-width:300px;" src="https://cdn.loom.com/sessions/thumbnails/17fcd7d891fe496f9a6b8fb85ede66bb-7f8590d1d4bcc2fb-full-play.gif"> </a> </details>

[!NOTE] This project is not affiliated with or endorsed by the U.S. Securities and Exchange Commission. EDGAR and SEC are trademarks of the SEC.

Quick Start

{
  "mcpServers": {
    "sec-edgar-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "SEC_EDGAR_USER_AGENT=Your Name (your@email.com)",
        "stefanoamorelli/sec-edgar-mcp:latest"
      ]
    }
  }
}

The -i flag is required for MCP's JSON-RPC communication.

For other installation methods (pip, conda, uv), see the documentation.

Tools

CategoryTools
CompanyCIK lookup, company info, company facts
Filings10-K, 10-Q, 8-K retrieval, section extraction
FinancialsBalance sheet, income statement, cash flow (XBRL-parsed)
Insider TradingForm 3/4/5 transactions

All responses include SEC filing URLs for verification.

HTTP Transport

For platforms like Dify, use streamable HTTP instead of stdio:

python -m sec_edgar_mcp.server --transport streamable-http --port 9870

No authentication is included. Use only on private networks.

Evaluations

Promptfoo-based test suite. See evals/ for details.

cd evals && npm install && npm run eval

Documentation

Full docs: sec-edgar-mcp.amorelli.tech

Contributors

<a href="https://github.com/stefanoamorelli/sec-edgar-mcp/graphs/contributors"> <img src="https://contrib.rocks/image?repo=stefanoamorelli/sec-edgar-mcp" /> </a>

Citation

If you use this software in research, please cite it:

DOI

@software{amorelli_sec_edgar_mcp_2025,
  title = {{SEC EDGAR MCP (Model Context Protocol) Server}},
  author = {Amorelli, Stefano},
  version = {1.0.6},
  year = {2025},
  month = {9},
  url = {https://doi.org/10.5281/zenodo.17123166},
  doi = {10.5281/zenodo.17123166}
}

See CITATION.cff for additional formats.

License

AGPL-3.0. For commercial licensing: stefano@amorelli.tech

Related MCP servers

Access 800,000+ Federal Reserve economic time series through Claude and Cursor with FRED® data integration.

117
TypeScript
AGPL-3.0
View repository →

28 pay-per-event tools for regulatory, sanctions, procurement, and corporate-registry monitoring.

0
Python
MIT
View repository →
RLRLM Tools logo

Persistent Python sandbox for token-efficient codebase exploration—reduce context usage by 25-35% with server-side code analysis.

8
Python
MIT
View repository →

Discover and explore Azure Verified Modules from the Bicep Public Registry

Check messages, npm packages and crypto addresses before acting. Read-only scanner tools.

0
JavaScript
AGPL-3.0
View repository →

Dutch-learning market map: schools, Verified Pro tutors, exams, paths and courses near any capital.