sec-ai: SEC EDGAR MCP Server

by lkcair Your server? Claim it

local only

sec-ai: SEC EDGAR runs on your own machine — the client starts it, so there is no endpoint to ping. 189 installs a week from pypi. Last commit 21 Oct 2026.

SEC EDGAR in 22 tools: 10-K/10-Q/8-K text, XBRL facts, insider trades, 13F, full-text search.

Installs per day peak 1 574 · avg 71 · -90% w/w

a month agotoday

189

Installs / week

pypi · sec-finance-ai

Stars

0 open issues

21 Oct 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check sec-ai: SEC EDGAR every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add sec-ai -- uvx sec-finance-ai

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "sec-ai": {
      "command": "uvx",
      "args": [
        "sec-finance-ai"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.sec-ai]
command = "uvx"
args = ["sec-finance-ai"]

.cursor/mcp.json

{
  "mcpServers": {
    "sec-ai": {
      "command": "uvx",
      "args": [
        "sec-finance-ai"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "sec-ai": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "sec-finance-ai"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: SEC_USER_AGENT (Name and e-mail sent to the SEC, e.g. 'Jane Doe [email protected]'. A built-in default is used if unset).

Alternatives to sec-ai: SEC EDGAR

same job, measured the same way

SecFeed: SEC EDGAR filings

by secfeedapi

SEC EDGAR data as tools: filing search, full text, XBRL financials, insider trades, 13F, 8-K events.

40 tools answering

SEC EDGAR

by danishashko

SEC EDGAR filings (10-K, 10-Q, 8-K), XBRL financials, and full-text filing search. No API key.

116 installs/wk local only

Filingrail MCP

by adamhudson777

SEC EDGAR financials, insider trades, 8-K events, and 13F holdings as MCP tools.

135 installs/wk local only

Sec Edgar Filings MCP

by dancerdan15

SEC EDGAR filings, full-text search & XBRL financial facts

answering

SEC EDGAR Insider Trades & Financials

by monriah-studio

SEC EDGAR for agents: Form 4 insider trades, cluster buys, filings, XBRL financials and search.

7 tools answering

FilingSpy

by filingspy

SEC filings as tools: 13F superinvestor portfolios, Form 4 insider trades, XBRL and filing text

answering

EDGAR Answers

by aion-autonomous-org

Normalized SEC EDGAR data for AI agents: XBRL financials, 10-K risk diffs, Form 4 insider trades.

answering

Edgar MCP

by mrfentmen

SEC EDGAR company filings, XBRL facts, and full text search for public companies. No key required.

147 installs/wk local only

sec-ai: SEC EDGAR — questions

Answers built from our own checks of this server.

Why is there no uptime for sec-ai: SEC EDGAR?

sec-ai: SEC EDGAR runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package sec-finance-ai was installed 189 times last week.

How do I connect sec-ai: SEC EDGAR?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls sec-finance-ai straight from pypi; nothing to host, nothing to sign up for.

How many people use sec-ai: SEC EDGAR?

The pypi package sec-finance-ai was installed 189 times in the last week. Week over week that is -90%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is sec-ai: SEC EDGAR open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.