This project provides a Model Context Protocol (MCP) server for accessing U.S. Securities and Exchange Commission (SEC) EDGAR filings. It enables AI assistants to retrieve company filings, financial statements, and insider trading data with exact numeric precision, built upon the edgartools library. The primary benefit is facilitating structured, precise data access for financial analysis and AI-driven insights from public company disclosures.

How It Works

This project implements a Model Context Protocol (MCP) server, built on edgartools, to provide AI assistants with precise access to SEC EDGAR filings. It acts as a data gateway, translating AI queries into structured requests for company information, financial statements (XBRL-parsed), and insider trading data. The core advantage lies in its ability to deliver exact numeric precision and direct SEC filing URLs for verification, enhancing trust and auditability in AI-driven financial analysis. An optional streamable HTTP transport is available for integration with platforms like Dify.

Quick Start & Requirements

• Primary install / run command: docker run -i --rm -e "SEC_EDGAR_USER_AGENT=Your Name (your@email.com)" stefanoamorelli/sec-edgar-mcp:latest
• Non-default prerequisites: A valid SEC_EDGAR_USER_AGENT environment variable is required. Alternative installation methods (pip, conda, uv) are detailed in the documentation.
• Documentation: Full documentation is available at sec-edgar-mcp.amorelli.tech.

Highlighted Details

• Comprehensive Data Access: Supports CIK lookups, company facts, retrieval of 10-K, 10-Q, 8-K filings, and specific section extraction.
• Precise Financials: Provides XBRL-parsed financial statements, including Balance Sheets, Income Statements, and Cash Flows.
• Insider Trading Data: Enables retrieval of Form 3, 4, and 5 transaction details.
• Verifiable Outputs: All responses include direct SEC filing URLs, allowing for easy verification and audit.

Maintenance & Community

The project is maintained by Stefano Amorelli. No specific community links (Discord, Slack) or detailed contributor information beyond the primary author are provided in the README.

Licensing & Compatibility

• License: AGPL-3.0.
• Commercial Use: Requires a separate commercial license; contact stefano@amorelli.tech for inquiries. The AGPL-3.0 license may impose copyleft restrictions on derivative works.

Limitations & Caveats

The streamable HTTP transport option lacks authentication and should only be used on private networks. The project is not affiliated with or endorsed by the SEC.