@node2flow/gemini-file-search-rag-mcp

v1.0.2

Published

2 months ago

MCP server for Gemini RAG — manage File Search stores, upload documents, and query with AI-powered retrieval-augmented generation

0High
0Medium
0Low

node2flow

gemini rag mcp model-context-protocol file-search ai claude cursor google retrieval-augmented-generation

Gemini File Search RAG MCP Server

MCP (Model Context Protocol) server for Google's Gemini File Search (RAG). Manage file search stores, upload documents, and query with RAG through 12 tools.

Works with Claude Desktop, Cursor, VS Code, and any MCP client.

Quick Start

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "gemini-rag": {
      "command": "npx",
      "args": ["-y", "@node2flow/gemini-file-search-rag-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

Cursor / VS Code

Add to MCP settings:

{
  "mcpServers": {
    "gemini-rag": {
      "command": "npx",
      "args": ["-y", "@node2flow/gemini-file-search-rag-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

HTTP Mode (Streamable HTTP)

For remote deployment or shared access:

GEMINI_API_KEY=your_key npx @node2flow/gemini-file-search-rag-mcp --http

Server starts on port 3000 (configurable via PORT env var). MCP endpoint: http://localhost:3000/mcp

Configuration

| Environment Variable | Required | Description | |---|---|---| | GEMINI_API_KEY | Yes | Google Gemini API key (get one here) | | PORT | No | Port for HTTP server (default: 3000, only used with --http) |

All Tools (12 tools)

Store Management (4 tools)

| Tool | Description | |---|---| | gemini_create_store | Create a new file search store | | gemini_list_stores | List all file search stores | | gemini_get_store | Get store details | | gemini_delete_store | Delete a store (with optional force) |

Upload & Import (2 tools)

| Tool | Description | |---|---| | gemini_upload_to_store | Upload content directly to a store (text, base64) | | gemini_import_file_to_store | Import an existing Gemini file into a store |

Operations (2 tools)

| Tool | Description | |---|---| | gemini_get_operation | Check status of a store operation | | gemini_get_upload_operation | Check status of an upload operation |

Document Management (3 tools)

| Tool | Description | |---|---| | gemini_list_documents | List documents in a store | | gemini_get_document | Get document details | | gemini_delete_document | Delete a document from a store |

RAG Query (1 tool)

| Tool | Description | |---|---| | gemini_rag_query | Query documents using RAG with Gemini models |

Requirements

Node.js 18+
Google Gemini API key

How to Get a Gemini API Key

Go to Google AI Studio
Click "Create API key"
Copy the key and use it as GEMINI_API_KEY

For Developers

git clone https://github.com/node2flow-th/gemini-files-search-rag-mcp-community.git
cd gemini-files-search-rag-mcp-community
npm install
npm run build

# Run in stdio mode
GEMINI_API_KEY=your_key npm start

# Run in dev mode (hot reload)
GEMINI_API_KEY=your_key npm run dev

# Run in HTTP mode
GEMINI_API_KEY=your_key npm start -- --http

License

MIT License - see LICENSE