Gemini DeepSearch MCP is an automated research agent that leverages Google Gemini models and Google Search to perform deep, multi-step web research.
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
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Low — 1 query, 1 loop, Flash modelMedium — 3 queries, 2 loops, Flash modelHigh — 5 queries, 3 loops, Pro modelTesting — With Langsmith tracing bash GEMINI_API_KEY=AI******* LANGSMITH_API_KEY=ls******* LANGSMITH_TRACING=true make inspectmacOS — Edit ~/Library/Application Support/Claude/claude_desktop_config.json:Windows — The Windows tool exposed by this serverLinux — The Linux tool exposed by this serverGEMINI_API_KEY environment variableCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"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.
GEMINI_API_KEY environment variable| Variable | Description | Required |
|---|---|---|
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| LANGSMITH_API_KEY | Credential the server authenticates with. | Yes |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.