Sandbox
@stefanoamorelli/sec-edgar-mcp

MCP server for SEC EDGAR filings

SEC EDGAR MCP connects an agent to SEC company filings, financial statements, and insider trading records. It exposes tools for CIK lookup, company info, filing retrieval, section extraction, and XBRL-parsed financial statements, with source URLs for verification.

356 stars94 forksPythonUpdated 27d ago
Who it's for

Builders who want their agent to look up public-company filings and financial data on demand.

What it delivers

You can ask an agent to pull verified SEC filing data instead of hunting through EDGAR yourself.

What it does

Company lookup tools

Find a company’s CIK, company info, and company facts from EDGAR.

Filing retrieval

Get 10-K, 10-Q, and 8-K filings and extract specific sections.

Financial statement parsing

Read balance sheet, income statement, and cash flow data parsed from XBRL.

Insider trading access

Inspect Form 3, 4, and 5 transactions.

HTTP transport option

Run the server over streamable HTTP with `python -m sec_edgar_mcp.server --transport streamable-http --port 9870`.

Evaluation suite

Use the `evals/` Promptfoo setup to test the server’s responses.

How to get it

  1. 1For platforms like Dify, use streamable HTTP instead of stdio
    python -m sec_edgar_mcp.server --transport streamable-http --port 9870
  2. 2Promptfoo-based test suite. See evals/ for details.
    cd evals && npm install && npm run eval

README

SEC EDGAR MCP

PyPI Python: 3.11+ License: AGPL-3.0 DOI Evals

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 sec-edgar-toolkit.

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

See demo video

[!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, 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

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

Files in the repo

Repository payload21 top-level entries
  • .github
  • docs
  • evals
  • scripts
  • sec_edgar_mcp
  • tests
  • .env.example
  • .gitignore
  • AUTHORS
  • CITATION.cff
  • CONTRIBUTORS
  • Dockerfile
  • LICENSE
  • mypy.ini
  • pyproject.toml
  • README.md
  • sec-edgar-mcp-logo.png
  • SECURITY.md
  • server.json
  • uv.lock
  • VERSIONING.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k