How do I install the knowledge-rag (uvx) MCP server?

You can install the knowledge-rag (uvx) MCP server with one click using McpMux. Download the free McpMux desktop app from mcpmux.com/download, open it, find knowledge-rag (uvx) in the server registry, and click Install. McpMux automatically configures the server for your AI client — whether it's Cursor, Claude Desktop, VS Code, ChatGPT, Windsurf, or JetBrains.

Which AI clients support the knowledge-rag (uvx) MCP server?

The knowledge-rag (uvx) MCP server works with all MCP-compatible AI clients including Cursor, Claude Desktop, Claude Code, VS Code (GitHub Copilot), ChatGPT, Windsurf, JetBrains IDEs, Zed, Cline, Gemini CLI, and Amazon Q Developer. McpMux acts as a universal gateway — configure knowledge-rag (uvx) once and all your AI clients can use it.

Back to Registry

knowledge-rag (uvx) MCP Server

Community

Contributed by Lyon.

Local RAG for Claude Code. Hybrid semantic + BM25 search with cross-encoder reranking, 13 MCP tools, 20 format parsers, async background reindex, file watcher, and GPU CUDA support. Zero external servers required.

Install with McpMux Source Code Docs

About the knowledge-rag (uvx) MCP Server

The knowledge-rag (uvx) MCP server is a local (stdio) Model Context Protocol server available in the McpMux registry. Local RAG for Claude Code. Hybrid semantic + BM25 search with cross-encoder reranking, 13 MCP tools, 20 format parsers, async background reindex, file watcher, and GPU CUDA support. Zero external servers required. This is a community-contributed MCP server by Lyon..

Install the knowledge-rag (uvx) MCP server with one click using McpMux. It works with Cursor, Claude Desktop, Claude Code, VS Code, ChatGPT, Windsurf, JetBrains, and any MCP-compatible AI client. No authentication required — install and start using it immediately.

Transport Configuration

12345678910{
  "type": "stdio",
  "command": "uvx",
  "args": [
    "knowledge-rag"
  ],
  "metadata": {
    "inputs": []
  }
}

Details

TransportLocal (stdio)

Hostinglocal

AuthNone required

Capabilities

Tools

Links

Repository Homepage Documentation

Supported AI Clients

The knowledge-rag (uvx) MCP server works with all MCP-compatible AI clients through McpMux:

CursorClaude DesktopClaude CodeVS CodeChatGPTWindsurfJetBrainsZedClineGemini CLIAmazon Q

Related MCP Servers

Perplexity (npx)

AI-powered search using Perplexity models. Provides web search, deep research, and reasoning capabilities with real-time web context.

Exa Search (Remote)

AI-powered web search that understands meaning, not just keywords. Hosted remote MCP server, no local setup required.

Exa Search (npx)

AI-powered web search that understands meaning, not just keywords. Find similar pages, search by content type, and get clean text from any URL via npx.

ElevenLabs (uvx)

Generate speech, clone voices, create sound effects, and manage audio with the ElevenLabs API. Text-to-speech, voice design, and audio isolation.

Pinecone (npx)

Manage Pinecone vector database indexes and records. Create indexes, upsert vectors, query by semantic similarity, and manage namespaces.

Qdrant (uvx)

Store and retrieve information from Qdrant vector database using semantic search. Supports local and cloud Qdrant instances.

Install knowledge-rag (uvx) with McpMux

One-click install from the McpMux desktop app. Auto-configures for Cursor, Claude, VS Code, ChatGPT, Windsurf, JetBrains, and any MCP-compatible client.

Install