Back to Apps

Rust Local RAG
by ksaritek
High-performance local RAG server in Rust. Search PDF documents privately using Ollama embeddings without external API calls.
0 stars
Works in:claude
Exposes:Tools
What it does
Rust Local RAG is a privacy-focused retrieval-augmented generation system that connects local PDF documents to AI assistants via the Model Context Protocol. It allows users to perform semantic searches over their own document collections entirely on-device, ensuring that sensitive data never leaves the local machine.
Tools
search_documents: Performs semantic similarity search across indexed PDFs using a query string.list_documents: Returns a comprehensive list of all documents currently indexed in the system.get_stats: Provides system metrics including embedding counts and memory usage.
Installation
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"rust-local-rag": {
"command": "/Users/yourusername/.cargo/bin/rust-local-rag",
"env": {
"DATA_DIR": "/Users/yourusername/Documents/data",
"DOCUMENTS_DIR": "/Users/yourusername/Documents/rag",
"LOG_DIR": "/tmp/rust-local-rag",
"LOG_LEVEL": "info",
"LOG_MAX_MB": "10"
}
}
}
}
Supported hosts
- Claude Desktop
Choose your AI client and follow the steps below.
Claude Desktop
Add to claude_desktop_config.json with DATA_DIR and DOCUMENTS_DIR env vars.





