SEC EDGAR MCP server

The MCP (Modular Computing Platform) server for EDGAR SEC data enables AI agents to access and analyze SEC filings such as proxy statements and Form 4 documents. It provides specialized tools to streamline the retrieval of executive compensation information and insider trading activities from SEC data.

Installation

To use the edgar-sec-mcp server, you'll need to configure it as an extension in your Goose environment. Follow these steps to set it up:

Adding as a Goose Extension

Add the following configuration to your Goose YAML configuration file:

extensions:
  edgar-sec-mcp:
    args:
    - --from
    - git+https://github.com/flothjl/edgar-sec-mcp@main
    - edgar-sec-mcp
    cmd: uvx
    enabled: true
    envs: {}
    name: edgar-sec 
    type: stdio
GOOSE_MODEL: gpt-4o-mini
GOOSE_PROVIDER: openai

This configuration:

• Installs the extension directly from GitHub
• Sets up the server to run as a stdio extension in Goose
• Uses gpt-4o-mini as the default model through OpenAI

Available Tools

The edgar-sec-mcp server provides two primary tools for accessing SEC data:

GetProxyStatementTablesByTicker

This tool allows you to retrieve tables from proxy statements for a specific company ticker. Proxy statements contain valuable information about:

• Executive compensation
• Board members
• Corporate governance
• Shareholder voting matters

GetForm4ByTicker

Use this tool to access Form 4 filings for a specific company ticker. Form 4 documents reveal:

• Insider trading activities
• Stock transactions by company executives and directors
• Changes in beneficial ownership

Usage Examples

To use the edgar-sec-mcp tools in your AI agent applications, you can make calls to these endpoints through Goose. Here are basic usage patterns:

Retrieving Proxy Statement Tables

# Example of retrieving proxy statement tables for Apple
response = await agent.use_tool("GetProxyStatementTablesByTicker", {"ticker": "AAPL"})

Accessing Form 4 Filings

# Example of getting Form 4 filings for Tesla
insider_trading_data = await agent.use_tool("GetForm4ByTicker", {"ticker": "TSLA"})

By integrating these tools into your AI agent workflows, you can easily access regulatory financial data without having to parse complex SEC documents manually.

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.