{
"mcpServers": {
"gemini-search": {
"env": {
"GEMINI_API_KEY": "your_gemini_api_key_here"
},
"args": [
"--transport",
"stdio"
],
"command": "gemini-mcp"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Is it safe?
No known CVEs for git.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 299 days ago. 52 stars.
Will it work with my client?
Transport: stdio, http. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'git' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Dynamic problem-solving through sequential thought chains
A Model Context Protocol server for searching and analyzing arXiv papers
An open-source AI agent that brings the power of Gemini directly into your terminal.
The official Python SDK for Model Context Protocol servers and clients
MCP Security Weekly
Get CVE alerts and security updates for Gemini Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
[!NOTE]
The MCP server is currently available underhttps://gemini-mcp-server-231532712093.europe-west1.run.app/mcp/. It is deployed to Google Cloud Run and can be authenticated using an AI Studio API key. see examples/test_remote.py for an example on how to use the server with thegoogle-genaiclient.
A Model Context Protocol server that provides access to Google's Gemini API. This server enables LLMs to perform intelligent web searches, generate content, and access other Gemini features. It supports both STDIO and streamable-http transport modes and can be run locally or remotely. If you use STDIO mode it will try to use the GEMINI_API_KEY environment variable. If you use streamable-http mode it will try to use the Bearer token in the Authorization header.
Available Tools:
query (string, required): The search query to executeinclude_citations (boolean, optional): Whether to include citations in the response. Default is False.prompt (string, required): The prompt or task for Gemini.model (string, optional): The Gemini model to use. Default is gemini-2.5-flash-preview-05-20.pip install git+https://github.com/philschmid/gemini-mcp-server.git
GEMINI_API_KEY environment variableGEMINI_API_KEY="your_gemini_api_key_here" gemini-mcp --transport stdio
gemini-mcp --transport streamable-http
The server will start on http://0.0.0.0:8000/mcp/
You can deploy the Gemini MCP Server as Remote MCP Server to Google Cloud Run to make it available easily available to any client.
To deploy the server, run the following command from your terminal, replacing [PROJECT-ID] and [REGION] with your Google Cloud project ID and desired region:
# Set your project ID and region
export PROJECT_ID=remote-mcp-test-462811
export REGION=europe-west1
export SERVICE_NAME=gemini-mcp-server
# Authenticate with Google Cloud
gcloud auth login
gcloud config set project $PROJECT_ID
# Enable required services
gcloud services enable run.googleapis.com artifactregistry.googleapis.com cloudbuild.googleapis.com
# Deploy the service
gcloud run deploy $SERVICE_NAME \
--source . \
--region $REGION \
--port 8000 \
--allow-unauthenticated
The command will build the Docker image, push it to Google Artifact Registry, and deploy it to Cloud Run. After the deployment is complete, you will get a URL for your service. We will allow unauthenticated access to the service this means that anyone with the URL can send requests to the server, which it self is protected by an Authorization header. If you want to secure the service you can follow the instructions in the Cloud Run documentation.
cleanup
SERVICE_NAME=gemini-mcp-server
REGION=europe-west1
gcloud run services delete $SERVICE_NAME --region $REGION
Add to your mcpServers configuration:
STDIO Mode:
{
"mcpServers": {
"gemini-search": {
"command": "gemini-mcp",
"args": ["--transport", "stdio"],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key_here"
}
}
}
}
HTTP Mode:
{
"mcpServers": {
"gemini-mcp": {
"url": "https://remote-mcp-test.com/mcp/", // replace with your remote mcp server url
"headers": { "Authorization": "Bearer YOUR_KEY" } // replace with your AI Studio API key
}
}
}
or check out the example in the [examples/test_remote.py](exa