marc-shade/world-intel-mcp
120-tool MCP server for real-time global intelligence: markets, SEC filings, conflict, military, cyber, climate, news, and 30+ domains. AI situation briefs that cite their sources, user-defined geofences with escalation scoring, cited daily digests, live SSE dashboard. MIT, no paid API keys.
What it solves
World Intelligence MCP Server provides AI agents with real-time global awareness across 30+ domains, including financial markets, geopolitical risk, military posture, and cyber threats. It eliminates the need for agents to manually query dozens of disparate public APIs by providing a unified interface for world events and semantic search over historical intelligence.
How it works
The project implements the Model Context Protocol (MCP), allowing AI agents (like Claude) to access 132 specialized tools. It uses a centralized async HTTP fetcher with circuit breakers to gather data from over 50 free public APIs. Data is stored in a SQLite cache for speed and a Qdrant vector store for semantic search. A background collector daemon continuously populates the vector store and monitors user-defined "Areas of Interest" (AOI) geofences.
Who it’s for
Developers building AI agents that require high-fidelity, real-time world data for strategic analysis, risk assessment, or situational awareness.
Highlights
- Massive Toolset: 132 MCP tools covering everything from SEC filings and central bank rates to military aircraft tracking and submarine cable health.
- Semantic Intelligence: Integrates Qdrant and FastEmbed to allow natural language queries across all accumulated data.
- Geospatial Awareness: Includes built-in datasets for critical infrastructure (nuclear facilities, spaceports, etc.) and support for custom AOI geofences.
- Ops-Center Dashboard: A map-first visual interface with live SSE feeds and circuit breaker health monitoring.
- Zero-Cost Data: All intelligence is sourced from free, public APIs, requiring no paid subscriptions.
Related
- Project
- Project
- Project
- Project
- Project