
marc-shade/world-intel-mcp 是从 https://github.com/marc-shade/world-intel-mcp. 导入的 MCP 服务器候选
概览
marc-shade/world-intel-mcp 是从 https://github.com/marc-shade/world-intel-mcp. 导入的 MCP 服务器候选
概述(AI 翻译)
跨30+域的实时全球智能,配备160个MCP工具、实时运营中心仪表盘、CLI和Qdrant向量存储,实现企业级语义搜索,跨越累积智能。所有数据均来自免费公开API:无需付费订阅。
为需要全球感知的人工智能代理打造:市场状况、地缘政治风险、军事态势、飞机队列预警、难民和移民流动、供应链中断、网络威胁等——所有内容均可通过模型上下文协议查询。矢量存储支持自然语言查询,如“台湾附近的军事活动”*或“针对医疗保健的网络威胁”*。
为了研究,收藏者会保留其捕获内容的过时历史。每个观察都包含其所描述的时期、已知的出版商发行日期以及保存时间,因此可以查询早期版本、修订后的数值、系列与过去日期之间的滞后相关性,收藏健康状况则从收藏者的运行日志中测量,而非从缓存新鲜度推断。
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
World Intelligence MCP Server
Real-time global intelligence across 30+ domains with 160 MCP tools, a live ops-center dashboard, a CLI, and a Qdrant vector store for enterprise-grade semantic search across accumulated intelligence. All data comes from free, public APIs: no paid subscriptions required.
Built for AI agents that need world awareness: market conditions, geopolitical risk, military posture, aircraft-cohort early warning, refugee and migration flows, supply chain disruptions, cyber threats, and more — all queryable via the Model Context Protocol. The vector store enables natural language queries like “military activity near Taiwan” or “cyber threats targeting healthcare” across all historical data.
For research, the collector keeps a dated history of what it captures. Each observation carries the period it describes, the publisher’s release date when known, and when it was saved, so earlier copies, revised values, lagged correlations between series and any past day can be queried, and collection health is measured from the collector’s run log rather than inferred from cache freshness. The server also exposes 29 MCP prompts (worked research questions, each naming the tools it needs and the limit to respect) and 3 MCP resources: a research guide generated from the live tool registry (intel://guide), a measures glossary (intel://guide/measures) and live source health (intel://guide/source-health).
What You Get
| Domain | Tools | Data Sources |
|---|---|---|
| Financial Markets | 7 | Yahoo Finance, CoinGecko, Alternative.me, Mempool |
| Forex & Currency | 3 | ECB/Frankfurter (8 major pairs, timeseries, cross rates) |
| Bonds & Yields | 2 | FRED, Yahoo Finance (yield curve, bond ETFs, spread analysis) |
| Earnings | 2 | Yahoo Finance (mega-cap calendar, surprise history) |
| SEC Filings | 3 | SEC EDGAR (full-text search, company filings, 8-K material events) |
| Company Enrichment | 1 | Yahoo Finance + GDELT + SEC + GitHub (composite profile) |
| News vs Market Reaction | 1 | RSS story clusters + Yahoo Finance daily bars + SEC ticker file (same-session move of named companies and country indices) |
| Macro Composite | 1 | Weighted 6-signal market verdict (Fear&Greed, VIX, sectors, DXY, BTC, yields) |
| Economic Indicators | 6 | AAA fuel prices, EIA energy, FRED macro, World Bank |
| Central Banks | 1 | 15 central bank policy rates |
安装
docker run -p 6333:6333 qdrant/qdrant配置
{
"mcpServers": {
"world-intel-mcp": {
"command": "world-intel-mcp"
}
}
}