Live stock, crypto, SEC filings, insider trades, FX and macro data for LLM agents.
MCPpedia last refreshed this data
io.github.adididitagain/finance-mcp is an MCP server that live stock, crypto, SEC filings, insider trades, FX and macro data for LLM agents. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 87/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"finance": {
"env": {
"SEC_USER_AGENT": "Your Name your@email.com"
},
"args": [
"-y",
"finance-data-mcp"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Live financial data for any LLM agent. Stock quotes · crypto · SEC filings · insider trades · XBRL financials · FX · macro
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'finance-data-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked finance-data-mcp against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml
MCP client bridge: connects to MCP servers and registers their tools on ctx.tools
The official MCP server implementation for the Perplexity API Platform
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration
MCP Security Weekly
Get CVE alerts and security updates for io.github.adididitagain/finance-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Live financial data for any LLM agent. Stock quotes · crypto · SEC filings · insider trades · XBRL financials · FX · macro
Most finance APIs want a signup, a key, and a credit card before your agent can answer "what's Apple trading at?"
finance-mcp wraps five genuinely free public sources behind eleven MCP tools. No key for any of them. The only configuration is an email address, and only because the SEC insists on one.
Company insiders — officers, directors, 10% owners — must report every trade in their own stock to the SEC within two business days. It's public, it's structured, and essentially nobody reads it.
The catch is that most of it means nothing. Options vest. Shares get withheld to pay the tax on that vesting. None of it is a decision, and all of it gets reported as "insider selling."
get_insider_activity separates the two. Real output, Apple, one week in June:
OPEN-MARKET (a deliberate decision to trade)
Sold: 5 filing(s) 302.92K shares ≈ $87,566,268.55
MECHANICAL (vesting, option exercises, tax withholding — no decision): 1 filing(s)
Newstead Jennifer — SVP, GC and Secretary
2026-06-15 +30.10K @ — Option exercise / conversion
2026-06-15 −16.24K @ $296.42 Shares withheld for taxes ← not a trade
LEVINSON ARTHUR D — Director
★ 2026-05-06 −149.53K @ $284.57 Open-market sale ← a real decision
★ 2026-05-06 −100.47K @ $285.04 Open-market sale
2026-05-06 −5.00K @ — Gift
Same company, same month. One of those is a signal; the other is payroll. Every row links to the filing it came from.
It reports what was disclosed and does not interpret it. Insider buying and selling both have innocent explanations, and neither predicts the share price.
That claim is testable, so we tested it: every Form 4 filed by an insider at an S&P 100 company over twelve months — 2,969 filings — classified by whether the filing contains an actual decision to trade.
Roughly seven in ten insider filings contain no decision to trade at all. At the median company it's 83%.
A second result surprised us more. Corporations file Form 4s too, as 10% owners — and 53 filings, 1.8% of the sample, accounted for 65% of every disposed share. The largest single "insider" in the data was Honeywell International Inc, disposing of 317M shares of a company it was spinning off. Rank insiders by share count and the top of the list isn't people.
Method, caveats and the raw data are in analysis/. It re-runs from scratch with two