semantic-mcp

# Semantic MCP [](https://pypi.org/project/semantic-mcp/) [](https://hub.docker.com/r/milkymap/semantic-mcp) Semantic router for MCP ecosystems - Discover, manage, and execute tools across multiple MCP servers with progressive disclosure. ## Overview `semantic-mcp` is a FastMCP-based MCP server that provides semantic discovery and lifecycle management for other MCP servers. It connects to a discovery service for semantic search and manages server lifecycles locally via ZMQ-based IPC. ``` LLM Client (Claude/Cline) │ MCP Protocol ▼ ┌─────────────────────────────┐ │ semantic-mcp │ │ (FastMCP MCP Server) │ ├─────────────────────────────┤ │ Discovery → Semantic API │ │ Execution → ZMQ + Sessions │ └─────────────────────────────┘ │ │ ▼ ▼ Discovery MCP Servers Service (stdio/http) ``` ## Installation ### Option 1: uvx (Recommended) ```bash uvx semantic-mcp serve --transport stdio ``` ### Option 2: pip/uv ```bash # Install from PyPI pip install semantic-mcp # Or with uv uv pip install semantic-mcp # Run semantic-mcp serve --transport stdio ``` ### Option 3: Docker ```bash docker pull milkymap/semantic-mcp:0.2 docker run -d \ -p 8001:8001 \ -e DISCOVERY_URL=http://your-discovery-service \ -e DISCOVERY_API_KEY=your-key \ milkymap/semantic-mcp:0.2 serve --transport streamable-http --port 8001 ``` ### Option 4: From source ```bash git clone https://github.com/milkymap/mcp_runtime cd mcp_runtime uv sync uv run semantic-mcp serve ``` ## Configuration ### Environment Variables | Variable | Description | Default | |----------|-------------|---------| | `DISCOVERY_URL` | Discovery service API URL | `http://localhost:8000` | | `DISCOVERY_API_KEY` | API key for discovery authentication | None | | `DISCOVERY_ENCRYPTION_KEY` | Key to decrypt s…