Skip to main content
Glama
SEC EDGAR MCP

SEC EDGAR MCP

by reblickulous

SEC EDGAR MCP for Claude Desktop

Logging into EDGAR for company lookups is no longer a chore! You can access a company's SEC filings directly through Claude — without navigating EDGAR's UI and ctrl-F'ing through 200 pages of filings.

This MCP connects Claude Desktop directly to SEC EDGAR so you can research public companies, pull filings, and extract financial data through conversation — no browser, no manual downloads, no copy-pasting into a spreadsheet.


What It Does

Four tools, all usable through natural language in Claude Desktop:

lookup_company — Find any public company's CIK number by name or ticker symbol. The CIK is EDGAR's internal identifier and the starting point for everything else.

search_filings — Pull a company's filing history filtered by type. Ask for their last five 10-Ks, recent 8-Ks, an S-1, Form D — whatever's relevant to what you're looking at.

fetch_filing — Retrieve and read the actual content of a filing. Strips the HTML and returns clean readable text so Claude can summarize, extract, or answer questions about it directly.

get_financials — The most useful one for deal work. Pulls structured financial data: revenue, gross profit, operating income, net income, EBITDA components, total assets, liabilities, cash, long-term debt, and EPS — across the last three annual periods and four quarters. Ideal for building company one-pagers and investment summaries.


Related MCP server: mcp-edgar

How I Use It

The workflow that saves the most time is comp analysis. Instead of pulling five 10-Ks manually and building a table by hand, I can do this in one conversation:

"Look up Veeva Systems, pull their last three years of financials, and compare revenue growth and operating margins to what we're seeing in [target company]'s projections."

Claude handles the retrieval, does the math, and flags the deltas. What used to take an hour of tab management takes a few minutes.


Setup

What you'll need:


Step 1 — Verify Node.js is installed

Open Command Prompt (search "cmd" in your Start menu) and type:

node --version

You should see something like v20.x.x. If you get an error, go install Node.js first from nodejs.org, then come back.


Step 2 — Download this project

Click the green Code button at the top of this page → Download ZIP. Unzip it somewhere easy to find, like C:\edgar-mcp\.


Step 3 — Install dependencies

Open Command Prompt. You need to navigate into the project folder. The easiest way on Windows:

  1. Open File Explorer and go to your C:\edgar-mcp\ folder

  2. Click the address bar at the top of the window

  3. Type cmd and hit Enter — this opens Command Prompt already pointed at that folder

Now run:

npm install

You'll see text scroll by as it downloads the required libraries. When it stops and returns to the prompt, you're done.


Step 4 — Add your email

The SEC requires a contact email in every API request. Open index.js in Notepad and find this line near the top:

"User-Agent": "EDGAR-MCP-Tool/1.0 (personal-use; contact@example.com)",

Replace contact@example.com with your actual email address. Save the file.


Step 5 — Register with Claude Desktop

Claude Desktop uses a config file to know which MCP servers to load. You need to add this project to it.

Open File Explorer, click the address bar, paste this and hit Enter:

%APPDATA%\Claude

Open claude_desktop_config.json in Notepad.

If the file is empty, paste this entire block:

{
  "mcpServers": {
    "sec-edgar": {
      "command": "node",
      "args": ["C:\\edgar-mcp\\index.js"]
    }
  }
}

If the file already has content (other MCPs configured), add just the "sec-edgar" block inside the existing "mcpServers": { } section, with a comma separating it from the previous entry. It should look like this:

{
  "mcpServers": {
    "some-other-mcp": { ... },
    "sec-edgar": {
      "command": "node",
      "args": ["C:\\edgar-mcp\\index.js"]
    }
  }
}

Important: Use double backslashes (\\) in the file path inside the JSON. Single backslashes will cause an error.

Save the file.


Step 6 — Restart Claude Desktop

Don't just close the window — you need a full quit. Right-click the Claude icon in your system tray (bottom-right corner of your taskbar) and click Quit. Then relaunch Claude Desktop from your Start menu or desktop shortcut.


Step 7 — Test it

In Claude Desktop, try:

"Look up Torrid Holdings on EDGAR"

If Claude runs the lookup_company tool and returns a CIK number, you're live. Try following up with:

"Pull their last three years of financials"


Troubleshooting

Claude doesn't seem to be using the EDGAR tools Make sure you fully quit Claude Desktop from the system tray — just closing the window isn't enough. It needs a complete restart to load new MCP configs.

"Cannot find module" error You need to run npm install inside the project folder. See Step 3.

HTTP errors from EDGAR Make sure you updated the User-Agent in index.js with a real email address. The SEC will eventually block requests with placeholder addresses.

The path in the config isn't working Double-check that the path in claude_desktop_config.json matches exactly where you put the files, and that you're using double backslashes (\\).


A Note on Limitations

XBRL structured financial data (get_financials) only works for public companies. Private companies file with the SEC but don't submit machine-readable financial tags, so this tool won't return data for them. For private company diligence, use fetch_filing to pull and read the actual document text.


Stack

  • Runtime: Node.js (v18+)

  • MCP SDK: @modelcontextprotocol/sdk

  • Data source: SEC EDGAR APIs — free, no auth required

  • Transport: stdio (local)


What's Next

  • Hosted version — deploy to Railway so colleagues can connect without local setup

  • Institutional ownership tool — pull 13F/13G/13D filings for cap table research

  • Full-text search — search across all EDGAR filings for specific language or deal terms

Available Tools

4 tools
fetch_filingA

Fetch and read the text content of a specific SEC filing. Use the cik, accession_number, and primary_document values returned by search_filings. Returns cleaned, readable text (HTML tags stripped). Long documents are truncated — ask for a specific section if needed.

Inputs: cik (required), accession_number (required), primary_document (required).

get_financialsA

Fetch structured financial data for a public company from SEC XBRL filings. Returns key metrics (revenue, gross profit, operating income, net income, EBITDA components, total assets, liabilities, cash, debt, EPS) for the last 3 annual periods and 4 quarters. Ideal for building company one-pagers and investment summaries.

Inputs: cik (required), annual_periods, quarterly_periods.

lookup_companyA

Search for a company on SEC EDGAR by name or ticker symbol. Returns CIK number and full legal name. Always run this first to get a CIK before searching filings.

Inputs: company_name (required).

search_filingsA

Get recent SEC filings for a company using its CIK number. Optionally filter by form type (10-K, S-1, 8-K, DEF 14A, etc.). Returns filing dates, accession numbers, and document names needed for fetch_filing.

Inputs: cik (required), limit, form_type.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 4 tools

    Disambiguation5/5

    The four tools form a clear pipeline: lookup_company resolves identity to a CIK, search_filings lists that company's filings, fetch_filing reads a specific document, and get_financials returns structured XBRL metrics. The only mild adjacency is fetch_filing vs get_financials, but one is raw text and the other is structured financial statements, so boundaries are clear.

    Naming Consistency5/5

    All four names follow a strict verb_noun snake_case convention (lookup_company, search_filings, fetch_filing, get_financials). Verbs vary but each is semantically apt for its action and the pattern is entirely predictable.

    Tool Count5/5

    Four tools is tight and well-scoped, with each tool earning a distinct place in the SEC research workflow. Nothing feels redundant or missing at the count level.

    Completeness4/5

    The core lifecycle—find company, list filings, read filing, pull structured financials—is fully covered with sensible chaining. Minor gaps exist (no cross-company full-text filing search and fetch_filing truncates long documents), but agents can work around these by targeting specific sections.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to download, parse, and analyze SEC EDGAR filings, including 10-K/Q reports, XBRL financial statements, and insider trading data. It provides structured access to institutional holdings, corporate events, and financial facts for comprehensive investment research.
      19
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to access SEC EDGAR data: search filings, extract sections, pull structured financials, and track insider transactions.
      20 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables querying of SEC EDGAR filings and financial data via natural language, offering tools for company lookup, filing retrieval, XBRL data, and full-text search.
      146 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to research US public company filings, financials, and insider transactions using SEC EDGAR data, with no API keys required. Provides tools for company lookup, recent filings, full-text search, financial facts, and insider activity.
      5
      1
      MIT