Rust Local RAG MCP server

Rust Local RAG is a high-performance system that integrates with Claude Desktop via the Model Context Protocol (MCP). It allows you to search and analyze PDF documents directly within Claude conversations while keeping all data processing local, ensuring privacy and security. This tool uses semantic search powered by local embedding models to help you find relevant information in your documents.

Installation Guide

Prerequisites

Before installing the Rust Local RAG server, you need to set up several dependencies:

# Install Rust
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

# Install Ollama
brew install ollama

# Install Poppler (for PDF parsing)
brew install poppler

# Start Ollama and install embedding model
make setup-ollama

Build and Install

Once you have the prerequisites in place, you can build and install the server:

git clone <this-repository>
cd rust-local-rag
make install

Configure Claude Desktop

Add the following configuration to your Claude Desktop settings file located at ~/Library/Application Support/Claude/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"
            }
        }
    }
}

Make sure to replace yourusername with your actual username.

Using Rust Local RAG

Adding Documents

To add PDFs to your searchable document collection:

# Add PDFs to documents directory
cp your-files.pdf ~/Documents/rag/

Searching Documents in Claude

After adding documents and restarting Claude Desktop, you can start searching your documents directly within Claude conversations. Here are some example prompts:

1. "Search my documents for information about X"
2. "Find references to Y in my uploaded PDFs"
3. "Summarize what my documents say about Z"

Available Tools

The Rust Local RAG server exposes three main tools to Claude:

1. Document Search

   • Performs semantic search across your document collection
   • Returns ranked search results with similarity scores
   • You can specify how many results to return

2. List Documents

   • Shows all indexed documents in your collection
   • Helps you verify which documents are available for search

3. System Statistics

   • Provides information about embedding counts and system performance
   • Useful for troubleshooting or monitoring system health

Technical Details

How It Works

The Rust Local RAG system follows this data flow:

1. Document Processing: PDFs are converted to text, then divided into chunks
2. Embedding Generation: Text chunks are converted to vector embeddings using local Ollama models
3. Indexing: Embeddings are stored in a local vector database
4. Search: When you search, your query is converted to an embedding and compared against stored document embeddings
5. Results: The most similar document chunks are returned as search results

Privacy Focus

All processing happens locally on your machine:

• No document content is sent to external servers
• Embeddings are generated locally using Ollama
• All data remains on your device

This privacy-first approach ensures your sensitive documents never leave your control while still providing powerful semantic search capabilities.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "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"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "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"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "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"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect