rag-mcp-server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
RAG MCP Server
MCP Server that gives Claude Code semantic search over your PDFs, code, and documents. Index once, query instantly — with exact citations and zero hallucinations.
Setup
1. Install
git clone https://github.com/Rubrum95/rag-mcp-server
cd rag-mcp-server
pip install .For OCR support (scanned PDFs):
pip install ".[ocr]"
# macOS
brew install tesseract
# Windows — download installer from:
# https://github.com/UB-Mannheim/tesseract/wiki
# Linux
sudo apt install tesseract-ocr tesseract-ocr-spa2. Connect to Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"rag": {
"command": "rag-mcp-server"
}
}
}Related MCP server: CodeSense MCP
Usage
Index a project
Ask Claude: "Index ~/projects/my-research"
→ Calls rag_index, processes all PDFs and code filesQuery documents
Ask Claude: "What does the paper say about ocean warming?"
→ Calls rag_query, returns exact text with page citationsUpdate with new files
Ask Claude: "Update the my-research index"
→ Calls rag_update, only processes new/changed filesList indexed projects
Ask Claude: "List my indexed projects"
→ Shows all projects with file/chunk countsConfiguration
Copy config.yaml to ~/.rag-mcp-server/config.yaml to customize:
embedding_model— default: multilingual model (Spanish + English)chunk_size/chunk_overlap— text splitting parameterstop_k— default number of search resultsocr_languages— Tesseract languages for scanned PDFssupported_extensions— file types to index
How It Works
Your files → Text extraction → Chunking → Embeddings → ChromaDB
(+ OCR if needed)
Your question → Embedding → Cosine similarity search → Top chunks
↓
Claude reads exact text
and responds with citationsRequirements
Python 3.10+
~500MB disk for embedding model (downloaded once)
Tesseract (optional, for scanned PDFs)
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Parse, extract, split, and ask over digital PDFs (text layer, no OCR) from Cursor and Claude.
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Your own memory inside ChatGPT and Claude, with the source of every note.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables Claude Desktop to search and query personal document collections (PDF, Word, Markdown, text) using semantic search and conversational AI with full context preservation across exchanges.MIT
- AlicenseNot gradedqualityDmaintenanceProvides semantic code intelligence to help users search, navigate, and analyze entire codebases using plain English. It enables Claude to perform architectural overviews, bug detection, and refactor suggestions through local semantic search and keyword indexing.MIT
- AlicenseAqualityAmaintenanceEnables local semantic search over documents and code for Claude Code and Claude Desktop, running entirely offline with local embeddings and vector storage.14424 PyPI7MIT
- AlicenseBqualityDmaintenanceEnables Claude Code to interact with Jupyter notebooks, perform semantic search over knowledge files, and manage research projects.334MIT