intelligence-hub-mcp
🌐 intelligence-hub-mcp
多领域情报收集、80:20 交叉综合与发布 MCP 服务器
并行收集多个不同尖端领域(AI/Vibe 编码、合成生物学、神经科学、加密资产、医疗、逆向工程)的最新动态,并进行 80:20 帕累托分离 和 异领域交叉点(Crossover)分析,输出结构化洞察的情报中枢 MCP 服务器。
🏛️ Hermes 生态系统与 Tri-MCP 架构
本 MCP 服务器在 Hermes AI Agent (Master Orchestrator) 的旗下,与学术深度挖掘(ocr-mcp-server)及自有媒体分发(news-site-coral)作为对等 peer 协同工作。
┌───────────────────────────────┐
│ 🪐 Hermes AI Agent │
│ (Master Orchestrator) │
└───────┬───────────────┬───────┘
│ │
┌───────────────┴────┐ ┌────┴──────────────┐
│ intelligence-hub-mcp│ │ ocr-mcp-server │
│ (80:20 Crossover) │ │ (Deep MAD Review) │
└────────────────────┘ └───────────────────┘
│ │
└─────────┬─────────┘
▼
┌───────────────────────────────┐
│ news-site-coral │
│ (WIRED Narrative Publishing) │
└───────────────────────────────┘多层采集(Intake)(
intake/):Type A (RSS/Atom): bioRxiv (SynthBio / Neuroscience), medRxiv, Zenn, Ethereum Research, Paradigm
Type B(公开 API): Hacker News (Firebase API), arXiv (Atom API)
Type C(浏览器/未公开 API): GitHub Trending (Phase 2)
智能跳过(Smart Skip): 根据
interval_hours判断,自动防止不必要的频繁请求
智能化与持久化 (
storage/&analysis/):LanceDB (PyArrow): 持久化
IntelligenceRecord元数据 + 768 维向量嵌入80:20 帕累托分析: 定点观测 80% + 偶发性飞地 20%
交叉提取(Crossover): 使用 LLM 提取不同领域之间的结构类比与相互应用可能性
发布与联动 (
mcp/):为结构化数据(
CrossoverDigest)附加suggested_themes/suggested_tags,通过 Hermes Agent 向 X(140 字推文串) / Note(随笔) / Coral Magazine(WIRED 型三段式 HTML) 进行多渠道分发。
Related MCP server: worldmonitor-mcp
🚀 快速开始
同步依赖
uv sync --all-groups运行测试
uv run pytest层边界验证 (Spaghetti Guard)
npx @naoya.k/spaghetti-guard check运行定期收集 CLI(Cron / 批量执行)
uv run intelligence-hub-cron启动 MCP 服务器(Stdio 传输)
uv run intelligence-hub-mcp🛠️ 公开的 MCP 工具
fetch_intelligence_feed(category=None, limit_per_channel=None, force_fetch=False): 并行获取最新 feed 并保存到 LanceDB(带interval_hours判断)search_intelligence(query, category=None, limit=10): 语义向量相似度搜索list_intelligence_records(category=None, is_serendipity=None, limit=50): 已保存文章的过滤列表generate_crossover_digest(period="daily", fetch_latest_first=True): 生成跨领域交叉点报告 & 带 Coral 推荐标签的结构化数据get_feed_status(): 查看监控中 feed 的设置、间隔状态及 LanceDB 统计
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
AlicenseBqualityCmaintenanceMCP server that turns any audio or video source into structured, searchable intelligence for agents, enabling download, transcription, semantic search, speaker identification, and more.224MIT- Alicense-qualityBmaintenanceMCP server wrapping worldmonitor global intelligence dashboard, exposing 140 tools across 32 services for live market, geopolitical, military, cyber, climate, and supply chain data.MIT
- FlicenseAqualityDmaintenanceMCP server that provides access to 14 OSINT data sources including government, research, corporate, and news APIs, enabling search, preview, and retrieval of public intelligence data.4
- Flicense-qualityCmaintenanceEditorial intelligence MCP server that helps agents discover stories worth writing about by analyzing primary sources, ranking angles, and turning signal into publishable drafts.
Related MCP Connectors
Autopilot MCP server for GEO analyses, reports, content, audits, memories and agents.
Social media analytics, video analysis, and competitor intel for any MCP-compatible AI agent.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/t012093/intelligence-hub-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server