Normalized SEC EDGAR data for AI agents: XBRL financials, 10-K risk diffs, Form 4 insider trades.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Give your agent answers from SEC EDGAR, not raw API responses.
This repository holds the documentation and registry manifest for a hosted MCP server. There is nothing to install or run: connect to the endpoint below from any MCP client. The server itself is operated as a managed service.
Every US public company files its financials with the SEC, for free, in XBRL. The catch is that "free and public" is not the same as "usable": companies tag the same line item a dozen different ways, annual and quarterly figures live in the same stream, restatements silently overwrite history, and Form 4 insider filings arrive as raw XML. Existing EDGAR MCP servers hand your agent that mess and wish it luck.
This server does the parsing first. Your agent asks for revenue; it gets revenue.
get_financials β normalized annual statementsMulti-year income statement, balance sheet, and cash flow for any US-listed company, from a ticker or CIK.
Behind that: an ordered tag-fallback chain per line item (filers disagree on
which us-gaap tag means "revenue"), duration filtering so annual figures aren't
contaminated by quarterly cumulatives, and restatement resolution to the most
recently filed value. Unreported items come back null rather than guessed.
filing_diff β what changed year over yearThe question an analyst actually asks β what did they start saying this year, and what did they quietly drop? β answered at paragraph level, with boilerplate that merely reflowed filtered out.
insider_activity β Form 4, parsedOpen-market buys separated from tax withholding and option exercises, so your agent doesn't mistake a scheduled vest for a conviction purchase.
filing_section β any section as clean textTable-of-contents decoys are filtered out; you get the real section body.
search_filings β full-text search since 2001Streamable HTTP endpoint:
Authenticate with your Apify API token as a bearer token. In an MCP client config:
For clients that only speak stdio, bridge with npx mcp-remote <url> --header "Authorization: Bearer YOUR_APIFY_TOKEN".
The server runs in standby mode: it scales to zero when idle and wakes on your first request, so the first call after a quiet period takes a few seconds.
Pay per successful call β failed calls are not billed.
| Call | Price |
|---|---|
search_filings | $0.005 |
get_financials | $0.02 |
insider_activity | $0.02 |
filing_section | $0.03 |
filing_diff | $0.05 |
Source data is SEC EDGAR β US government filings, public domain. Requests are made with a declared User-Agent and rate-limited well under the SEC's published ceiling, per their access guidelines. Nothing here is scraped from a site that prohibits it.
get_financials says so rather than guessing.filing_diff compares the two most recent filings of a form; arbitrary
filing pairs aren't exposed yet.Found a parsing bug or want a tool that isn't here? Open an issue here or on the Actor β specific reports about specific tickers get fixed.
Listed on the Apify Store. Documentation in this repository is Β© Aion; the service is proprietary.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/edgar-answers)<a href="https://allmcps.com/mcp/edgar-answers"><img src="https://allmcps.com/api/badge/edgar-answers?style=directory" alt="EDGAR Answers on AllMCPs" /></a>