Gemini DeepSearch MCP

Gemini DeepSearch MCP is an automated research agent that leverages Google Gemini models and Google Search to perform deep, multi-step web research. It generates sophisticated queries, synthesizes information from search results, identifies knowledge gaps, and produces high-quality, citation-rich answers.

- Automated multi-step researchusing Gemini models and Google Search
- FastMCP integrationfor both HTTP API and stdio deployment
- Configurable effort levels(low, medium, high) for research depth
- Citation-rich responseswith source tracking
- LangGraph-powered workflowwith state management

Start the LangGraph development server with Studio UI:

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

GEMINI_API_KEY=AI LANGSMITH_API_KEY=ls LANGSMITH_TRACING=true make inspect

- 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

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

Stdio MCP Server(Claude Desktop integration):

- file_path: Path to a JSON file containing the research results

The stdio MCP server writes results to a JSON file in the system temp directory to optimize token usage. The JSON file contains the sameanswerandsourcesdata as the HTTP version, but is accessed via file path rather than returned directly.

- Python 3.12+
- GEMINI_API_KEYenvironment variable

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

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 } } }

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 } } }

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 } } }

- Replaceyour-gemini-api-key-herewith your actual Gemini API key
- Restart Claude Desktop after updating the configuration
- Set ample timeout to avoidMCP error -32001: Request timed out

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-mcpwith the actual absolute path to your project directory.

Once configured, you can use thedeep_searchtool 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"

The deep search agent is from theGemini Fullstack LangGraph Quickstartrepository.

Search and extract information about research papers from arXiv.