RAG_MCP

RAG_MCP

A RAG-ready MCP server for semantic PDF search with OCR, FAISS, and transformers—plug into any MCP client and retrieve intelligent answers within your MCP client.

Step 1: Create virtual env and install requirements

curl -LsSf https://astral.sh/uv/install.sh | sh uv init rag_mcp cd rag_mcp uv venv source .venv/bin/activate uv pip install -r requirements.txt brew install tesseract

Step 2a: Add config to the Claude MCP client

code ~/Library/Application\ Support/Claude/claude_desktop_config.json ... { "mcpServers": { "rag": { "command": "/Users/XXX/.local/bin/uv", "args": [ "--directory", "/Users/XXX/Documents/RAG_MCP", "run", "rag.py" ] } } }

Step 2b: Add config to the Cursor MCP client

code ~/.cursor/mcp.json ... { "mcpServers": { "rag": { "command": "/Users/XXX/Documents/RAG_MCP/start.sh", "args": [] } } }

Step 5: Make MCP server executable

chmod +x start.sh chmod +x rag.py

Step 6: Run MCP server (Claude Desktop)

uv run rag.py

Step 7: Run MCP client and query

Parse the pdfs and tell me about 18 Church St. and what significance it has.

License

Apache License, Version 2.0

-
security - not tested
-
license - not tested
-
quality - not tested

local-only server

The server can only run on the client's local machine because it depends on local resources.

A Retrieval-Augmented Generation server that enables semantic PDF search with OCR capabilities, allowing users to query document content through any MCP client and receive intelligent answers.

  1. Step 1: Create virtual env and install requirements
    1. Step 2a: Add config to the Claude MCP client
      1. Step 2b: Add config to the Cursor MCP client
        1. Step 5: Make MCP server executable
          1. Step 6: Run MCP server (Claude Desktop)
            1. Step 7: Run MCP client and query
              1. License

                Related MCP Servers

                • A
                  security
                  F
                  license
                  A
                  quality
                  An MCP server that provides a tool to extract text content from local PDF files, supporting both standard PDF reading and OCR capabilities with optional page selection.
                  Last updated -
                  1
                  5
                  Python
                  • Apple
                • -
                  security
                  F
                  license
                  -
                  quality
                  An MCP server that enables searching and retrieving content from Confluence documentation systems, providing capabilities for both document searches and full page content retrieval.
                  Last updated -
                  Python
                • A
                  security
                  A
                  license
                  A
                  quality
                  An open-source platform for Retrieval-Augmented Generation (RAG). Upload documents and query them ⚡
                  Last updated -
                  1
                  169
                  JavaScript
                  MIT License
                • A
                  security
                  A
                  license
                  A
                  quality
                  A server that enables OCR capabilities to recognize text from images, PDFs, and Word documents, convert them to Markdown, and extract key information.
                  Last updated -
                  3
                  60
                  5
                  JavaScript
                  MIT License

                View all related MCP servers

                ID: bdrzg9wgq1