agentic-rag-mcp

enached134-ctrl/agentic-rag-mcp

★ 1 stars Python AI/LLM Updated 10d ago

Multi-agent RAG (LangGraph) exposed as an MCP server: plan -> retrieve -> synthesize -> self-critique with citations. Claude + pgvector + Voyage + Firecrawl.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentic-rag-mcp": {
      "command": "uvx",
      "args": [
        "agentic-rag-mcp"
      ]
    }
  }
}

Or install with pip: pip install agentic-rag-mcp

README Excerpt

<p align="center"> <img src="docs/img/01-architecture.png" alt="Agentic RAG — Multi-Agent Graph" width="880"> </p> A **multi-agent Retrieval-Augmented Generation system exposed as an MCP server**. Ask a question and a [LangGraph](https://langchain-ai.github.io/langgraph/) pipeline plans the retrieval, pulls evidence from a **pgvector** knowledge base, optionally augments it with

Tools (3)

askingestsearch

Topics

ai-agentsanthropicclaudefastmcplanggraphmcpmodel-context-protocolpgvectorragvector-search

agentic-rag-mcp

Quick Install

README Excerpt

Tools (3)

Topics

Related AI/LLM Servers