rag

fscottmiller/rag
★ 0 stars Python Database Updated today
Ultralight RAG server supporting MCP and API interactions
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": {
    "rag": {
      "command": "uvx",
      "args": [
        "rag"
      ]
    }
  }
}

Or install with pip: pip install rag

README Excerpt

A small, local Retrieval-Augmented Generation (RAG) service. It stores documents and embeddings in SQLite, then exposes the same index through REST and MCP. The default database is in memory for a zero-setup local experience. Set `RAG_DATABASE_PATH` to use file-backed SQLite when data should survive process restarts.

Tools (20)

MCP_HOSTMCP_PATHMCP_PORTMCP_TRANSPORTRAG_AUTH_MODERAG_CHUNKERRAG_CHUNK_OVERLAPRAG_CHUNK_SIZERAG_DATABASE_PATHRAG_EMBEDDING_API_KEYRAG_EMBEDDING_BATCH_SIZERAG_EMBEDDING_DIMENSIONSRAG_EMBEDDING_MODELRAG_EMBEDDING_PROVIDERRAG_EMBEDDING_TIMEOUTRAG_EMBEDDING_URLRAG_MAX_DOCUMENT_BYTESRAG_PROXY_ADMIN_ROLERAG_PROXY_READER_ROLERAG_PROXY_ROLE_HEADER
📊
Working with market or time-series data?
The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.
View dataset →