---

name: midos-mcp version: 1.0.0 description: MidOS — The MCP Knowledge OS. 134 tools for knowledge management, multi-agent orchestration, search, planning, and memory. 670K+ vectors, 46K+ chunks, EUREKA synthesis. homepage: https://midos.dev metadata: {"clawdbot":{"emoji":"🧠","category":"knowledge","api_base":"https://midos.dev/mcp"}}

MidOS MCP — The Knowledge Operating System

MidOS is a knowledge middleware layer for AI agents. It gives you access to a continuously growing intelligence base: 670K+ vectors, 46K+ knowledge chunks, 451 EUREKA insights, and 134 MCP tools for search, memory, planning, and orchestration.

Think of MidOS as your agent's long-term brain.

What You Get

Quick Start

Connect via MCP (JSON-RPC 2.0)

# Health check
curl https://midos.dev/mcp/health

# Initialize session
curl -X POST https://midos.dev/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"my-agent","version":"1.0"}}}'

Search the knowledge base

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "smart_search",
    "arguments": {
      "query": "your topic here",
      "mode": "hybrid",
      "limit": 5
    }
  }
}

Save a memory

{
  "method": "tools/call",
  "params": {
    "name": "mem_save",
    "arguments": {
      "content": "User prefers concise responses with code examples",
      "type": "preference",
      "project": "my-project"
    }
  }
}

Create a plan

{
  "method": "tools/call",
  "params": {
    "name": "create_plan",
    "arguments": {
      "goal": "Build a new feature",
      "tasks": "1. Research existing patterns\n2. Design API\n3. Implement\n4. Test"
    }
  }
}

Knowledge Base Stats (live)

• 46,283 knowledge chunks across AI, engineering, research, strategy
• 670K+ vector embeddings (Gemini gemini-embedding-001, 3072-d)
• 451 EUREKA synthesized insights
• 139 SOTA benchmarks
• φ = 0.932 knowledge coherence score

Key Features

🔍 Hybrid Search (BM25 + Semantic)

Combines keyword precision with semantic understanding. Outperforms vector-only by 9.3% on relevance benchmarks.

🧠 Persistent Memory

mem_save / mem_search backed by LanceDB. Memories survive across sessions. 91.67% hit@5 on recall benchmarks.

📋 Smart Planning

Create structured multi-step plans, track progress, checkpoint completions. Survives context resets.

⚡ Fast Preflight

knowledge_preflight checks for duplicate knowledge in 19ms (title cache, 48K+ chunks). Prevents knowledge bloat.

🏗️ Quality Gate

quality_gate scores content on 7 dimensions before adding to the knowledge base. Keeps signal-to-noise high.

Heartbeat Integration

Add to your agent's periodic check-in:

## MidOS (every session start)
1. Call where_was_i(client="your-agent-name") to resume context
2. Call mem_context(scope="recent") to load recent memory
3. Before creating knowledge: knowledge_preflight(topic)
4. After important decisions: mem_save(content, type="decision")

Self-Hosted Option

MidOS is open source. Run your own instance:

git clone https://github.com/MidOSresearch/midos-core
cd midos-core
python -m modules.mcp_server.midos_mcp --http --port 3100

Full docs: https://midos.dev/docs GitHub: https://github.com/MidOSresearch/midos-core