MCP-RAG
Verified IntegrationClient Configuration
— Connect MCP-RAG to Claude Desktop or Cursor in seconds{
"mcpServers": {
"mcp-rag": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-rag"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Orchestrates multi-agent AI workflows for business analysis by combining Model Context Protocol (MCP) with Retrieval-Augmented Generation (RAG).
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for MCP-RAG
Yes, MCP-RAG boasts a modular design allowing extensive customization. Users can easily replace sample data with their own, add custom analytics tools, extend RAG capabilities with new knowledge sources, and swap LLM backends (like Google Gemini or custom localhost APIs).
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.