MCP Documentation Server

Semantic search server for MCP (Model Context Protocol) documentation using Redis embeddings.

THE MCP MCP for MCPing MCP's

Setup

python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Usage

1. Scrape documentation: python url_scraper.py
2. Create embeddings: python embed_to_redis.py
3. Run MCP server: python doc_mcp_server.py

Tools

• search_docs - Semantic search through documentation
• list_documents - List all available documents
• fetch_file - Retrieve specific file content

MCP Client Config

{
  "mcpServers": {
    "doc-embeddings": {
      "command": "bash",
      "args": ["-c", "cd /path/to/mcp/server && source venv/bin/activate && python doc_mcp_server.py"],
      "env": {}
    }
  }
}

Files

• url_scraper.py - Scrapes MCP from mcp and convert to markdown
• embed_to_redis.py - Creates embeddings from headings and stores in Redis
• doc_mcp_server.py - FastMCP server providing search functionality
• repo_scraper.py - Processes code repositories to markdown
• output/ - Processed documentation files