AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Investment & VC › world-intel-mcp
✦ Free & open sourceInvestment & VC

world-intel-mcp

160-tool MCP server for real-time global intelligence and markets.

World Intelligence MCP Server

Real-time global intelligence, markets, and risk analysis for AI agents via Model Context Protocol.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
7.3
ZEKAI
Essential MCP intelligence hub
Free & open source · Investment & VC
Ease of setup4
Usefulness9
Maintenance9.5
Community6.5
★ 1,048
GITHUB
Oct 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

World Intelligence MCP Server provides 160 tools spanning 30+ domains, including financial markets, SEC filings, prediction markets, and military posture. Designed for investment professionals and traders building AI agents that require grounded, real-time geopolitical and macroeconomic awareness.

Runs on
Cross-platform
Hosting
Self-host
Languages
Python
License
MIT

What it is

It aggregates data from free public APIs—such as Yahoo Finance, FRED, SEC EDGAR, and ACLED—into a unified MCP interface, CLI, and Qdrant vector store. It tracks dated observation histories, exposes 29 research prompts, and powers a live ops-center dashboard with SSE.

Who it's for

Suits quantitative researchers, systematic traders, and venture capital analysts building custom AI agents with Claude or Cursor. Not suitable for non-technical users who require a plug-and-play SaaS terminal without writing code or managing Python environments.

Key features

160 MCP Tools

Query financial markets, SEC filings, conflict data, and supply chains directly through the Model Context Protocol.

Qdrant Vector Store

Enables enterprise-grade semantic search across accumulated historical intelligence using natural language.

Prediction Markets

Compares Polymarket and Kalshi event contracts side-by-side with match confidence and Brier scoring.

AOI Geofences

Defines custom areas of interest in three shapes to monitor hotspot escalation and reverse-geocoded local news.

How to start

Up and running in 3 steps

1
Clone the repository and run pip install -e . to install the package.
2
Configure your MCP client (such as Claude Code or Cursor) to point to the world-intel-mcp command.
3
Optionally install the dashboard and vector extras to run the Streamlit UI and Qdrant semantic search.
Real talk

Our honest verdict

What's great

  • Covers 30+ intelligence domains from liquidity and bonds to military posture and cyber threats without paid API keys.
  • Maintains a dated observation history with revisions and lagged correlations between series for backtesting research.
  • Includes 29 worked research prompts and 3 MCP resources for guided querying.
  • Comes with a live ops-center dashboard and SSE support alongside standard stdio MCP mode.

Where it falls short

  • Requires local installation and Python 3.11+ environment management.
  • Optional vector store and dashboard features require installing extra dependencies like Qdrant and Streamlit.
  • Relying entirely on free public APIs means source endpoints can occasionally change structure or rate limit.
Cost

Pricing & license

Free under its open-source license. The only cost is running it yourself on your own hardware or infrastructure.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: world-intel-mcp for Investment & VC
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure world-intel-mcp for you — and train your team.
Get it done for you ↗
Questions

FAQ

Do I need paid API subscriptions to run this?

No. All data is pulled from free, public APIs without requiring paid subscriptions or proprietary keys.

How do I query the historical intelligence data?

You can use the built-in Qdrant vector store integration for natural language semantic search across all accumulated observations.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Investment & VC — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google