Install
$ agentstack add mcp-i3t4an-claude-gemini-mcp-integration-server Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Pipes remote content directly into a shell (remote code execution).
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Claude-Gemini MCP Integration Server
> Enable direct collaboration between Claude Code and Google's Gemini AI models through the Model Context Protocol (MCP)
[](https://www.python.org/downloads/) [](https://modelcontextprotocol.io/) [](https://opensource.org/licenses/MIT)
Overview
The Claude-Gemini MCP Integration Server bridges Claude Code and Google's Gemini AI models, enabling seamless AI-to-AI collaboration within your development workflow. Ask Gemini questions, get code reviews, and brainstorm solutions directly from Claude Code.
Key Features
- Direct AI Collaboration: Claude can consult Gemini for different perspectives
- Smart Code Reviews: Get Gemini's analysis on security, performance, and best practices
- Creative Brainstorming: Leverage Gemini's creativity for problem-solving
- One-Command Setup: Complete installation in under 2 minutes
- Easy Integration: Works seamlessly with Claude Code CLI
Quick Start
Prerequisites
- Python 3.8+ - Download here
- Claude Code CLI - Install with:
npm install -g @anthropic-ai/claude-code - Gemini API Key - Get free at Google AI Studio
Installation
Option 1: Automated Install (Recommended)
curl -sSL https://raw.githubusercontent.com/i3T4AN/Claude-Gemini-MCP-Integration-Server/main/install.sh | bash
Option 2: Manual Setup
# Clone the repository
git clone https://github.com/i3T4AN/Claude-Gemini-MCP-Integration-Server.git
cd Claude-Gemini-MCP-Integration-Server
# Run setup with your API key
chmod +x setup.sh
./setup.sh YOUR_GEMINI_API_KEY
Usage
Starting Claude Code
claude
Accessing Tools
In Claude Code, use the /mcp command to access MCP tools:
/mcp
Available Tools
1. ask_gemini - Direct Questions
Ask Gemini anything and get the response in Claude's context:
mcp__claude-gemini-integration__ask_gemini
Example prompts:
- "What are the latest Python best practices for async programming?"
- "Explain quantum computing in simple terms"
- "Compare React vs Vue for a new project"
2. gemini_code_review - Code Analysis
Get comprehensive code reviews focusing on specific areas:
mcp__claude-gemini-integration__gemini_code_review
Focus areas:
general- Overall code quality and best practicessecurity- Security vulnerabilities and concernsperformance- Optimization opportunitiesmaintainability- Code clarity and structure
3. gemini_brainstorm - Creative Solutions
Brainstorm ideas and solutions with additional context:
mcp__claude-gemini-integration__gemini_brainstorm
Example topics:
- "Mobile app architecture for a social platform"
- "Database design for high-traffic e-commerce"
- "Marketing strategies for developer tools"
Configuration
API Key Management
The setup script automatically configures your API key. If you need to change it:
- Environment Variable (Recommended):
``bash export GEMINI_API_KEY="your-new-api-key" ``
- Direct Edit:
``bash nano ~/.claude-mcp-servers/claude-gemini-integration/server.py # Update the API_KEY variable ``
Advanced Configuration
Temperature Control
Adjust response creativity in ask_gemini:
0.0- Focused, deterministic responses0.5- Balanced (default)1.0- Creative, varied responses
Model Selection
The server uses gemini-2.0-flash by default. To use different models, edit server.py:
model = genai.GenerativeModel('gemini-1.5-pro') # For more powerful responses
Architecture
System Components
┌─────────────────┐ ┌──────────────────────┐ ┌─────────────────┐
│ Claude Code │◄──►│ MCP Integration │◄──►│ Gemini API │
│ CLI │ │ Server │ │ │
└─────────────────┘ └──────────────────────┘ └─────────────────┘
Protocol Details
- Protocol: JSON-RPC 2.0 over stdin/stdout
- MCP Version: 2024-11-05
- Transport: Standard MCP server communication
API Limits & Costs
Gemini Free Tier
- Rate Limit: 15 RPM (requests per minute)
- Daily Limit: 1,500 requests per day
- Token Limit: 32,000 tokens per minute
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: i3T4AN
- Source: i3T4AN/Claude-Gemini-MCP-Integration-Server
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.