SSyncDev

Deepsearch MCP Server

Gemini DeepSearch MCP is an automated research agent that leverages Google Gemini models and Google Search to perform deep, multi-step web research.

Local serverstdioPython

What is the Deepsearch MCP Server?

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

What the server does

  • Automated multi-step research — using Gemini models and Google Search
  • FastMCP integration — for both HTTP API and stdio deployment
  • Configurable effort levels — (low, medium, high) for research depth
  • Citation-rich responses — with source tracking
  • LangGraph-powered workflow — with state management

Credentials and setup notes

  • Python 3.12+ - GEMINI_API_KEY environment variable

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Deepsearch MCP Server

{
  "mcpServers": {
    "deepsearch": {
      "command": "uvx",
      "args": ["install"],
      "env": {
        "GEMINI_API_KEY": "your-value",
        "LANGSMITH_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.12+ - GEMINI_API_KEY environment variable
VariableDescriptionRequired
GEMINI_API_KEYCredential the server authenticates with.Yes
LANGSMITH_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • “Use Deepsearch to Low.”
  • “Use Deepsearch to Medium.”
  • “Use Deepsearch to High.”

Frequently asked questions

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 Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.

Alternatives to the Deepsearch MCP Server

Fetch

Official

Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.

Search & Web ScrapingPython★ 63.0k

Firecrawl

Official

Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.

Search & Web ScrapingTypeScript★ 4.6k

Rattlesnakesbymail

Dated, sourced claims about AI crawlers and agents, offered as MCP tools.

Search & Web ScrapingRemote

LexLint: compliance lint for AI, scraping, and privacy law

Compliance lint for AI, scraping, and privacy law. Cited findings in 200 or more jurisdictions.

Search & Web ScrapingRemote

Offprint

Publish your agent's Markdown as shareable web pages with revision provenance and comments.

Search & Web ScrapingRemote

Webbersites-x402-data-api

45 pay-per-call AI agent tools: scraping, SEO, crypto data, lint, agent memory. x402 USDC on Base.

Search & Web ScrapingRemote