Agentic Doc Search RAG
Verified IntegrationClient Configuration
— Connect Agentic Doc Search RAG to Claude Desktop or Cursor in seconds{
"mcpServers": {
"agentic-doc-search-rag": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-agentic-doc-search-rag"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
A self-corrective Agentic RAG system built with LangGraph that eliminates LLM hallucinations through intelligent relevance grading of retrieved documents before answering. It features a Streamlit UI for interaction, multi-turn conversation memory, and seamless integration as an MCP server tool for AI agents.
7/21/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Agentic Doc Search RAG
It employs a self-corrective, agentic architecture built with LangGraph. Instead of a linear path, it includes a dedicated 'grade_documents' node that intelligently assesses the relevance of retrieved information before any answer generation. If documents are irrelevant, it routes to a 'no_answer' state, avoiding fabrication.
Related MCP Servers
Browse all servers →Provides comprehensive historical and real-time crypto market data, including orderbooks, trades, candles, and more, from Hyperliquid, HIP-3, and Lighter.xyz.
Facilitates gasless blockchain transactions and interactions directly from Claude AI conversations.
Bridges Claude AI with blockchain networks, enabling gasless transactions, swaps, and transfers directly from natural language conversations.