Gemini MCP Server
MCP server that enables Claude Code to interact with Google's Gemini API for code analysis, chat, and summarization tasks.
README
Gemini MCP Server
MCP server that enables Claude Code to interact with Google's Gemini API directly.
Features
- gemini_analyze: Send prompts for code review, explanations, research
- gemini_chat: Multi-turn conversations with context
- gemini_summarize: Summarize large codebases/documents (1M token window)
Quick Start
# 1. Clone and build
git clone <this-repo> && cd gemini-mcp
npm install && npm run build
# 2. Set API key in ~/.zshrc
export GEMINI_API_KEY="your-key-here"
source ~/.zshrc
# 3. Add to ~/.claude.json (see config below)
# 4. Restart Claude Code
Setup
1. Get Gemini API Key
Get your free API key from: https://aistudio.google.com/apikey
2. Set Environment Variable
Add to your ~/.zshrc (or ~/.bashrc):
export GEMINI_API_KEY="your-api-key-here"
Then reload: source ~/.zshrc
3. Configure Claude Code
IMPORTANT: Add to
~/.claude.json, NOT~/.claude/settings.json
Add this to the mcpServers object in ~/.claude.json:
{
"mcpServers": {
"gemini-mcp": {
"type": "stdio",
"command": "node",
"args": ["/Users/buckmike/Projects/gemini-mcp/build/index.js"],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}
Claude Code supports ${VAR} syntax for environment variable expansion.
4. Restart Claude Code
Exit and relaunch Claude Code to load the new MCP server.
Usage
Once configured, Claude can use these tools:
| Tool | Purpose |
|---|---|
gemini_analyze |
Analyze code or answer questions using Gemini |
gemini_chat |
Have multi-turn conversations with context |
gemini_summarize |
Summarize large content (leverages 1M token window) |
Available Models
| Model | Description |
|---|---|
gemini-2.5-flash-preview-05-20 |
Fast, efficient (default) |
gemini-2.5-pro-preview-05-06 |
Best quality |
gemini-2.0-flash |
Stable release |
Troubleshooting
Tools Not Appearing After Restart
Most Common Cause: Config in wrong file.
| Wrong | Correct |
|---|---|
~/.claude/settings.json |
~/.claude.json |
Claude Code reads MCP servers from ~/.claude.json, not the settings.json file in the .claude directory.
Verification Steps:
-
Check config location:
cat ~/.claude.json | grep -A5 gemini-mcp -
Verify API key is set:
echo $GEMINI_API_KEY -
Test server manually:
echo '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}},"id":1}' | GEMINI_API_KEY="$GEMINI_API_KEY" node build/index.js -
Restart Claude Code completely (exit and relaunch)
Security
- API key stored in environment variable, never in code
- All inputs validated before API calls
- Errors handled gracefully
Development
npm install # Install dependencies
npm run build # Compile TypeScript
npm run dev # Watch mode for development
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.