Equity Intel Mcp
@cstamigo-droid
About Equity Intel Mcp
Stock intelligence for any LLM: SEC insider trades, superinvestor holdings (Dataroma), analyst consensus, valuation, options, and a composite ticker analysis. Runs on free/public data with graceful no-data handling (never fabricates a number).
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"equity-intel": {
"command": "python",
"args": [
"-m",
"equity_intel_mcp"
],
"cwd": "C:/path/to/equity-intel-mcp",
"env": {
"EDGAR_IDENTITY": "Your Name [email protected]"
}
}
}
}Tools
7**Hero tool.** Runs every source in parallel and returns one scored verdict (BUY → AVOID) with a per-source breakdown.
Net insider buying vs. selling from SEC **Form 4** filings (180-day window), weighted by USD value.
Which of ~80 tracked value investors hold the stock, plus recent net buying/selling.
Live price snapshot + position in the 52-week range.
Wall Street buy/hold/sell consensus — scored from distribution of strong-buy to strong-sell ratings.
1-month implied move (straddle/spot) + put/call OI skew. Primary use: risk-sizing.
Fair-value estimate (forward EPS × sector P/E) + financial-health score (debt, liquidity, margins).
Overview
What is Equity Intel MCP?
Equity Intel MCP is an institutional-grade equity analysis server for LLMs over the Model Context Protocol. It pulls insider buying, superinvestor holdings, analyst consensus, options-implied moves, and valuation from free/public data (SEC EDGAR, Yahoo Finance, Dataroma, Finnhub), then blends them into a single confidence-weighted verdict with a per-source breakdown.
How to use Equity Intel MCP?
Clone the repo, create a Python venv, install dependencies, set EDGAR_IDENTITY (and optionally FINNHUB_API_KEY) in .env, then run python -m equity_intel_mcp. For Claude Desktop, add the server configuration to claude_desktop_config.json. After setup, ask Claude questions like “Give me a full read on NVDA” or “Are insiders buying PLTR?”.
Key features of Equity Intel MCP?
- Institutional‑grade equity analysis for any LLM
- Blends multiple signals into a confidence‑weighted verdict
- Uses free public data (SEC EDGAR, Yahoo Finance, Dataroma)
- Graceful degradation: never fabricates a signal it lacks
- Uniform signal contract across all sources
- Resilient with per‑source TTL caching
Use cases of Equity Intel MCP?
- Get a holistic, scored stock analysis from a single MCP tool call
- Monitor insider buying/selling activity via SEC Form 4 filings
- Check which renowned value investors hold a stock and their recent trades
- Evaluate options‑implied moves for risk‑sizing a position
- Assess fair‑value estimate and financial health before a trade
FAQ from Equity Intel MCP
What data sources does Equity Intel MCP use?
SEC EDGAR (insider activity), Dataroma (superinvestor holdings), Yahoo Finance (quote, options, valuation), and Finnhub (analyst consensus). All are free/public, though Finnhub requires a free API key.
How does the server handle missing data?
If a source has no data, it returns “no signal” instead of a fake score. Missing data lowers the overall confidence but never invents a signal.
Is Equity Intel MCP investment advice?
No. It is for research and educational use only. Data comes from third‑party public sources and may be delayed or incomplete. Do your own due diligence.
What output formats are supported?
Every tool returns Markdown by default, or JSON when response_format="json" is specified for programmatic use.
How does the composite verdict work?
Each source produces a score (-100 to +100) and confidence (0–1). The composite weights each source by its importance multiplied by its own confidence, so thin signals don’t outvote strong ones.
Frequently asked questions
What data sources does Equity Intel MCP use?
SEC EDGAR (insider activity), Dataroma (superinvestor holdings), Yahoo Finance (quote, options, valuation), and Finnhub (analyst consensus). All are free/public, though Finnhub requires a free API key.
How does the server handle missing data?
If a source has no data, it returns “no signal” instead of a fake score. Missing data lowers the overall confidence but never invents a signal.
Is Equity Intel MCP investment advice?
No. It is for research and educational use only. Data comes from third‑party public sources and may be delayed or incomplete. Do your own due diligence.
What output formats are supported?
Every tool returns Markdown by default, or JSON when `response_format="json"` is specified for programmatic use.
How does the composite verdict work?
Each source produces a score (-100 to +100) and confidence (0–1). The composite weights each source by its importance multiplied by its own confidence, so thin signals don’t outvote strong ones.
Basic information
More Other MCP servers
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Website
FunnyWolfAdversary simulation and Red teaming platform with AI
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Comments