Gemini Deepsearch MCP

🚀 Gemini DeepSearch MCP

Gemini DeepSearch MCP is an automated research agent. It utilizes Google Gemini models and Google Search to conduct in - depth, multi - step web research. It can generate complex queries, synthesize information from search results, identify knowledge gaps, and provide high - quality, citation - rich answers.

✨ Features

• Automated multi - step research: Conducts research using Gemini models and Google Search.
• FastMCP integration: Supports both HTTP API and stdio deployment.
• Configurable effort levels: Allows users to set research depth as low, medium, or high.
• Citation - rich responses: Provides responses with source tracking.
• LangGraph - powered workflow: Comes with state management.

📦 Installation

Install directly using uvx:

uvx install gemini-deepsearch-mcp

💻 Usage Examples

Basic Usage

Development Server (HTTP + Studio UI)

Start the LangGraph development server with Studio UI:

make dev

Local MCP Server (stdio)

Start the MCP server with stdio transport for integration with MCP clients:

make local

Advanced Usage

Testing

Run the test suite:

make test

Test the MCP stdio server:

make test_mcp

Use MCP inspector

make inspect

With Langsmith tracing

GEMINI_API_KEY=AI******* LANGSMITH_API_KEY=ls******* LANGSMITH_TRACING=true make inspect

📚 Documentation

API

The deep_search tool accepts:

• query (string): The research question or topic to investigate
• effort (string): Research effort level - "low", "medium", or "high"
  • Low: 1 query, 1 loop, Flash model
  • Medium: 3 queries, 2 loops, Flash model
  • High: 5 queries, 3 loops, Pro model

Returns:

• answer: Comprehensive research response with citations
• sources: List of source URLs used in research

Requirements

• Python 3.12+
• GEMINI_API_KEY environment variable

Claude Desktop Integration

To use the MCP server with Claude Desktop, add this configuration to your Claude Desktop config file:

macOS

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "gemini-deepsearch": {
      "command": "uvx",
      "args": ["gemini-deepsearch-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      },
      "timeout": 180000
    }
  }
}

Windows

Edit %APPDATA%/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "gemini-deepsearch": {
      "command": "uvx",
      "args": ["gemini-deepsearch-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      },
      "timeout": 180000
    }
  }
}

Linux

Edit ~/.config/claude/claude_desktop_config.json:

{
  "mcpServers": {
    "gemini-deepsearch": {
      "command": "uvx",
      "args": ["gemini-deepsearch-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      },
      "timeout": 180000
    }
  }
}

⚠️ Important Note

• Replace your-gemini-api-key-here with your actual Gemini API key.
• Restart Claude Desktop after updating the configuration.
• Set ample timeout to avoid MCP error -32001: Request timed out.

Alternative: Local Development Setup

For development or if you prefer to run from source:

{
  "mcpServers": {
    "gemini-deepsearch": {
      "command": "uv",
      "args": ["run", "python", "main.py"],
      "cwd": "/path/to/gemini-deepsearch-mcp",
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      }
    }
  }
}

Replace /path/to/gemini-deepsearch-mcp with the actual absolute path to your project directory.

Once configured, you can use the deep_search tool in Claude Desktop by asking questions like:

• "Use deep_search to research the latest developments in quantum computing"
• "Search for information about renewable energy trends with high effort"

🔧 Technical Details

The deep search agent is from the Gemini Fullstack LangGraph Quickstart repository.

📄 License

This project is licensed under the MIT license.