local-pdf-rag-mcp

arjun7965/local-pdf-rag-mcp

★ 0 stars Python AI/LLM Updated today

A fully-local MCP server for question-answering over your PDFs. Ask in plain language; Claude retrieves only the relevant passages with page citations. On-device embeddings (sentence-transformers) + ChromaDB — no API keys, nothing leaves your machine.

View on GitHub → Try with Claude — $10 free →

Quick Install

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

Add to claude_desktop_config.json:

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

Or install with pip: pip install local-pdf-rag-mcp

README Excerpt

A fully-local [MCP](https://modelcontextprotocol.io) server that lets Claude (or any MCP client) answer questions over your PDFs. Point it at a PDF, ask questions in plain language, and the model fetches only the relevant passages — with page-level citations — instead of swallowing the whole document.

Tools (6)

PDF_RAG_DB_PATHPDF_RAG_EMBED_MODELPDF_RAG_RERANKPDF_RAG_RERANK_MODELPDF_RAG_TABLESuvx

local-pdf-rag-mcp

Quick Install

README Excerpt

Tools (6)

Related AI/LLM Servers