mcpbeat Sign in

MCP Gemini MCP Server

local only

MCP Gemini runs on your own machine — the client starts it, so there is no endpoint to ping. 549 installs a week from pypi. Last commit 1 Nov 2026.

MCP server for Google Gemini AI - text, image, video, research, and more

Installs per day peak 357 · avg 72 · +3% w/w
a month agotoday
549
Installs / week
pypi · mcp-gemini-crunchtools
0
Stars
1 open issue
1 Nov 2026
Last commit
from GitHub
AGPL-3.0
License
Python

What the code does

We read the source, 1 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Image runs as root Containerfile:31
USER 0

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add gemini -- uvx mcp-gemini-crunchtools
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "gemini": {
      "command": "uvx",
      "args": [
        "mcp-gemini-crunchtools"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.gemini]
command = "uvx"
args = ["mcp-gemini-crunchtools"]
.cursor/mcp.json
{
  "mcpServers": {
    "gemini": {
      "command": "uvx",
      "args": [
        "mcp-gemini-crunchtools"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "gemini": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-gemini-crunchtools"
      ]
    }
  }
}

Alternatives to MCP Gemini

same job, measured the same way
Google Image
by codechap

MCP server for Google Gemini image generation and editing

local only
Gemini
by houtini-ai

Model Context Protocol server for Google Gemini AI with chat, research, and grounding

5 335 installs/wk local only
MCP Serp
by acedatacloud

MCP server for Google search results via SERP API

1 037 installs/wk answering
Media Gen MCP
by strato-space

MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation.

91 installs/wk local only
MCP Veo
by acedatacloud

MCP server for Google Veo AI video generation

980 installs/wk answering
Brave Search MCP Server
by brave

Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.

34 601 installs/wk local only
MCP Nano Banana
by codefi

MCP server for Google Nano Banana (Gemini) image generation

111 installs/wk local only
Google Custom Search MCP
by a1-x-tech

MCP server for Google Custom Search: web and image search via a Programmable Search Engine.

55 installs/wk local only

MCP Gemini — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP Gemini?
MCP Gemini runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mcp-gemini-crunchtools was installed 549 times last week.
How do I connect MCP Gemini?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls mcp-gemini-crunchtools straight from pypi; nothing to host, nothing to sign up for.
How many people use MCP Gemini?
The pypi package mcp-gemini-crunchtools was installed 549 times in the last week. Week over week that is +3%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is MCP Gemini open source?
Yes — it is published under the AGPL-3.0 licence, written in Python, 0 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.