SEC EDGAR MCP Server

MCP (Model Context Protocol) server providing AI agents with direct access to SEC EDGAR financial data — 13M+ SEC filings, XBRL financial statements, and company information for 10,000+ US public companies.

What is MCP?

Model Context Protocol is an open standard for connecting AI agents to external data sources. This Actor runs as an MCP server that any compatible AI client (Claude, Cursor, Windsurf, etc.) can connect to.

Tools Available

search_filings

Search SEC filings via full-text search. Filter by form type (10-K, 10-Q, 8-K), date range, and keywords.

Parameters:

• query (required): Company name, ticker, or keyword
• max_results: 1-100 (default: 20)
• form_types: Comma-separated form types (e.g. "10-K,10-Q")
• start_date / end_date: Date filters (YYYY-MM-DD)

get_financial_data

Retrieve XBRL financial data for a company — revenue, net income, assets, and 1000+ other metrics.

Parameters:

• ticker (required): Ticker symbol or CIK number (e.g. "AAPL", "320193")
• metrics: Comma-separated XBRL metric names (e.g. "Revenues,NetIncomeLoss")
• max_results: 1-500 (default: 100)

get_company_info

Get company details and recent filing history — SIC code, state, fiscal year, exchanges, and more.

Parameters:

• ticker (required): Ticker symbol or CIK number
• include_filings: Include filing history (default: true)
• filing_types: Filter filing types
• max_filings: 1-100 (default: 20)

resolve_ticker

Resolve a ticker symbol to CIK number, or validate a CIK.

Parameters:

• identifier (required): Ticker or CIK to resolve

How to Connect

Standby URL

https://aligned-kettledrum--sec-edgar-mcp-server.apify.actor/mcp

Claude Desktop Configuration

{
  "mcpServers": {
    "sec-edgar": {
      "type": "url",
      "url": "https://aligned-kettledrum--sec-edgar-mcp-server.apify.actor/mcp"
    }
  }
}

Python (MCP Client)

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    url = "https://aligned-kettledrum--sec-edgar-mcp-server.apify.actor/mcp"
    async with streamablehttp_client(url) as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()
            result = await session.call_tool(
                "search_filings",
                {"query": "Apple 10-K", "max_results": 5}
            )
            print(result)

Data Source

All data comes from the official SEC EDGAR system:

• EFTS: Full-text search index for SEC filings
• XBRL: Structured financial data (company facts)
• Submissions: Company info and filing history

No API key required. SEC requests max 10 requests/second — the server handles rate limiting automatically.

FAQ

Q: What financial metrics are available? A: The XBRL API provides 1,000+ metrics including Revenues, NetIncomeLoss, Assets, Liabilities, StockholdersEquity, EarningsPerShareBasic, and many more US GAAP and IFRS metrics.

Q: How current is the data? A: Data updates in real-time as companies file with the SEC. Most 10-K/10-Q filings appear within minutes of submission.

Q: Can I search by CIK number instead of ticker? A: Yes. All tools accept both ticker symbols (AAPL) and CIK numbers (320193 or CIK0000320193).

Q: What form types can I search for? A: All SEC form types including 10-K (annual), 10-Q (quarterly), 8-K (current events), S-1 (registration), DEF 14A (proxy), and 100+ others.

Q: Is there a rate limit? A: The server respects SEC's 10 req/sec limit automatically. No additional rate limiting is needed on the client side.

Batch Processing

For large-scale data extraction (hundreds of filings), use the SEC EDGAR Financial Data Actor which supports bulk downloads with pagination.