Spark
Sign In
MCP Connector

Access SEC EDGAR Financial Data

Access SEC EDGAR filings, financial statements, and insider trading data with exact numeric precision from XBRL-parsed reports.

Connect
Works with sec edgar
Stefano Amorelli
Maintainer?
91
Spark score
out of 100
Updated last month
Version 1.0.8
Models
universal
Add to Favorites

Why it matters

Connect AI models to SEC EDGAR for official corporate financial data, reports, and insider trading information. Enables precise document attribution and deterministic answers.

Outcomes

What it gets done

01

Retrieve company CIK, information, and facts.

02

Access latest filings and document content, including 8-K analysis.

03

Parse financial statements and XBRL data for precise attribution.

04

Analyze insider trading forms (3/4/5) with detailed transaction data.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-sec-edgar | bash

Capabilities

Tools your agent gets

lookup_cik

Look up a company's CIK (Central Index Key) identifier from the SEC EDGAR database.

get_company_information

Retrieve detailed company information including name, ticker, and business description.

get_company_facts

Extract company facts and financial metrics from SEC EDGAR filings.

get_latest_filings

Retrieve the most recent SEC filings for a specified company.

get_document_content

Fetch the full text content of a specific SEC filing document.

analyze_8k

Analyze Form 8-K filings to extract material events and key information.

extract_section

Extract specific sections from SEC filings using pattern-based search.

get_financial_statements

Retrieve parsed financial statements with direct XBRL data for precise attribution.

+3 tools

Overview

SEC EDGAR MCP Server

SEC EDGAR MCP connects an AI assistant to SEC filings - company info, 10-K/10-Q/8-K reports, XBRL-parsed financial statements, and insider trading forms - with source URLs on every response for verification. Use it for AI-assisted lookup of verifiable SEC filing data. Run the HTTP transport only on private networks since it includes no authentication.

What it does

SEC EDGAR MCP connects AI assistants to SEC EDGAR filings - company information, 10-K/10-Q/8-K reports, XBRL-parsed financial statements, and insider trading data - with exact numeric precision, built on the edgartools library. Every response includes the source SEC filing URL for verification.

When to use - and when NOT to

Use it when you want an AI assistant to look up a company's CIK, pull its filings (10-K annual, 10-Q quarterly, 8-K current reports) and extract specific sections, retrieve XBRL-parsed balance sheets/income statements/cash flow statements, or review Form 3/4/5 insider trading transactions - with source URLs for every fact so figures can be verified against the original filing. Do not run the HTTP transport mode on a public network - it includes no authentication and is intended for private-network use only (e.g., integrating with platforms like Dify).

Capabilities

  • Company: CIK lookup, company info, company facts.
  • Filings: retrieve 10-K, 10-Q, and 8-K filings, with section extraction.
  • Financials: balance sheet, income statement, and cash flow statement, parsed from XBRL data.
  • Insider trading: Form 3/4/5 transaction data.

How to install

{
  "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. pip, conda, and uv installation methods are also documented at sec-edgar-mcp.amorelli.tech/setup/quickstart. For HTTP transport (e.g., Dify integration): python -m sec_edgar_mcp.server --transport streamable-http --port 9870 - unauthenticated, private networks only. Requires Python 3.11+.

Who it's for

Financial analysts, researchers, and investors who want an AI assistant to pull verifiable SEC filing data - financials, insider trades, and specific report sections - directly from EDGAR instead of manually navigating the SEC website.

Source README

SEC EDGAR MCP

PyPI Conda Version Python: 3.11+ License: AGPL-3.0 Verified on MseeP 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 edgartools.

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

See demo video

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

Category Tools
Company CIK lookup, company info, company facts
Filings 10-K, 10-Q, 8-K retrieval, section extraction
Financials Balance sheet, income statement, cash flow (XBRL-parsed)
Insider Trading Form 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

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.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.