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.
Clone the repository:
git clone https://github.com/stefanoamorelli/sec-edgar-mcp.git
cd sec-edgar-mcp
Install dependencies:
uv init mcp
uv add "mcp[cli]"
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
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
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
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?
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.).
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.
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" }
}
}
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.
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:
get_submissions
get_company_concepts
get_xbrl_frames
This enables AI assistants to access official SEC filing data for financial research, investment analysis, and corporate transparency applications.
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.
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"
]
}
}
}
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.
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.