Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-gemini-deep-research Research the impact of AI on healthcare and produce a cited report."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server for Google Gemini Deep Research via live Chrome cookies (no API key required).
uvx mcp-gemini-deep-researchOr install globally:
pip install mcp-gemini-deep-researchRelated MCP server: Gemini Research MCP Server
Run as an MCP server (stdio):
mcp-gemini-deep-researchConfigure in your MCP client (e.g., Hermes, Cursor, etc.):
{
"mcpServers": {
"gemini-deep-research": {
"command": "uvx",
"args": ["mcp-gemini-deep-research"]
}
}
}Python 3.11+
Google Chrome signed into a Google account with access to Gemini Deep Research
macOS, Windows, or Linux
This server uses your live Chrome session cookies (__Secure-1PSID, __Secure-1PSIDTS) to authenticate with Google's Gemini web API — no API key needed. It runs the real autonomous Deep Research agent that plans, searches the web, reads sources, and synthesizes a cited report over several minutes.
gemini_deep_research(query: str, timeout: int = 600) — Run a deep research investigation. Returns a JSON report with ok, report (markdown), sources, elapsed_s, research_id, report_path, and stalled flag.
MIT
This server cannot be deployed
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for Google Veo AI video generation
