SEC EDGAR MCP server

Provides access to SEC EDGAR financial data through tools for retrieving company submissions, financial concepts, standardized facts, and XBRL frames for investment research and regulatory compliance.
Back to servers
Provider
Stefano Amorelli
Release date
Apr 02, 2025
Language
Python
Stats
56 stars

The SEC EDGAR MCP server provides AI models with access to the SEC's EDGAR database of company filings through the Model Context Protocol (MCP). This integration allows AI assistants to retrieve financial data directly from official SEC filings without manual searching.

Installation

Using Python

  1. Clone the repository:

    git clone https://github.com/stefanoamorelli/sec-edgar-mcp.git
    cd sec-edgar-mcp
    
  2. Install dependencies:

    uv init mcp 
    uv add "mcp[cli]"
    
  3. Configure SEC EDGAR API access by creating a .env file:

    SEC_EDGAR_USER_AGENT="Your Name ([email protected])"
    PYTHONPATH=/path/to/your/local/cloned/repo/sec-edgar-mcp
    
  4. Start the MCP server:

    uv run mcp install sec_edgar_mcp/server.py --env-file .env --name "SEC EDGAR MCP Server" --with secedgar==0.6.0a0
    

Using Docker

A pre-built Docker image is available:

docker pull stefanoamorelli/sec-edgar-mcp:latest
docker run -e SEC_EDGAR_USER_AGENT="Your Name ([email protected])" stefanoamorelli/sec-edgar-mcp:latest

Cline Configuration

To set up with Cline:

I want to add the MCP server for SEC EDGAR.
Here's the GitHub link: @https://github.com/stefanoamorelli/sec-edgar-mcp
Can you add it?

Available Tools

get_submissions

Fetches a company's filing history and basic information using their CIK.

Example call:

{
  "jsonrpc": "2.0",
  "id": 42,
  "method": "tools/call",
  "params": {
    "name": "get_submissions",
    "arguments": { "cik": "0000320193" }
  }
}

This returns information about Apple Inc., including its name, ticker, and recent filings (10-K, 10-Q, etc.).

get_company_concepts

Retrieves values for a specific financial concept (XBRL tag) for a company.

Example call:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_company_concepts",
    "arguments": {
      "cik": "0000320193",
      "taxonomy": "us-gaap",
      "tag": "AccountsPayableCurrent"
    }
  }
}

This returns a time series of Apple's "Accounts Payable, Current" values from financial statements.

get_company_facts

Returns all available XBRL facts for a company, providing a comprehensive dataset of financial information.

Example call:

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "get_company_facts",
    "arguments": { "cik": "0000320193" }
  }
}

get_xbrl_frames

Retrieves data for a specific financial concept across multiple companies or time periods.

Example call:

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "get_xbrl_frames",
    "arguments": {
      "taxonomy": "us-gaap",
      "tag": "AccountsPayableCurrent",
      "unit": "USD",
      "year": 2019,
      "quarter": 1
    }
  }
}

This returns "Accounts Payable, Current" values for all companies reporting this metric in Q1 2019.

Usage Example

Once the server is running, you can connect to it with any MCP-compatible client, such as an AI assistant or the MCP CLI tool. The client can then discover and use the available EDGAR tools.

For example, an AI assistant could:

  1. Request a company's recent filings using get_submissions
  2. Identify specific financial data points using get_company_concepts
  3. Compare financial metrics across companies using get_xbrl_frames

This enables AI assistants to access official SEC filing data for financial research, investment analysis, and corporate transparency applications.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later