Gemini MCP Server
# Gemini MCP Server
[](https://smithery.ai/server/mcp-server-gemini)
[](https://www.npmjs.com/package/mcp-server-gemini)
[](https://opensource.org/licenses/MIT)
[](https://www.typescriptlang.org/)
[](https://modelcontextprotocol.io/)
A powerful MCP (Model Context Protocol) server that brings Google's latest Gemini AI models to your favorite development environment. Access Gemini 2.5's thinking capabilities, vision analysis, embeddings, and more through a seamless integration.
š **Works with**: Claude Desktop, Cursor, Windsurf, and any MCP-compatible client
šÆ **Why use this**: Get Gemini's cutting-edge AI features directly in your IDE with full parameter control
š **Self-documenting**: Built-in help system means you never need to leave your editor
## Features
- **6 Powerful Tools**: Text generation, image analysis, token counting, model listing, embeddings, and self-documenting help
- **Latest Gemini Models**: Support for Gemini 2.5 series with thinking capabilities
- **Advanced Features**: JSON mode, Google Search grounding, system instructions, conversation memory
- **Full MCP Protocol**: Standard stdio communication for seamless integration with any MCP client
- **Self-Documenting**: Built-in help system - no external docs needed
- **TypeScript & ESM**: Modern, type-safe implementation
### Supported Models
| Model | Context | Features | Best For |
|-------|---------|----------|----------|
| gemini-2.5-pro | 2M tokens | Thinking, JSON, Grounding | Complex reasoning |
| gemini-2.5-flash ā | 1M tokens | Thinking, JSON, Grounding | General use |
| gemini-2.5-flash-lite | 1M tokens | Thinking, JSON | Fast responses |
| gemini-2.0-flash | 1M tokens | JSON, Grounding | Standard tasks |
| gemini-1.5-pro | 2M tokens | JSON | Legacy support |
## Quick Start
1. **Get Gemini API Key**
- Visit [Google AI Studio](https://makersuite.google.com/app/apikey)
- Create a new API key
- **IMPORTANT**: Keep your API key secure and never commit it to version control
2. **Configure Your MCP Client**
<details>
<summary><b>Claude Desktop</b></summary>
Config location:
- Mac: `~/Library/Application Support/Claude/claude_desktop_config.json`
- Windows: `%APPDATA%\Claude\claude_desktop_config.json`
- Linux: `~/.config/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"gemini": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:aliargun/mcp-server-gemini"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
}
```
</details>
<details>
<summary><b>Cursor</b></summary>
Add to Cursor's MCP settings:
```json
{
"gemini": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:aliargun/mcp-server-gemini"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
```
</details>
<details>
<summary><b>Windsurf</b></summary>
Configure in Windsurf's MCP settings following their documentation.
</details>
<details>
<summary><b>Other MCP Clients</b></summary>
Use the standard MCP stdio configuration:
```json
{
"type": "stdio",
"command": "npx",
"args": ["-y", "github:aliargun/mcp-server-gemini"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
```
</details>
3. **Restart Your MCP Client**
## How to Use
Once configured, you can use natural language in your MCP client to access Gemini's capabilities:
### Basic Commands
```
"Use Gemini to explain quantum computing"
"Analyze this image with Gemini"
"List all Gemini models"
"Get help on using Gemini"
```
### Advanced Examples
```
"Use Gemini 2.5 Pro with temperature 0.3 to review this code"
"Use Gemini in JSON mode to extract key points with schema {title, summary, tags}"
"Use Gemini with grounding to research the latest in quantum computing"
```
š **[See the complete Usage Guide](USAGE_GUIDE.md)** for detailed examples and advanced features.
## Why Gemini MCP Server?
- **Access Latest Models**: Use Gemini 2.5 with thinking capabilities - Google's most advanced models
- **Full Feature Set**: All Gemini API features including JSON mode, grounding, and system instructions
- **Easy Setup**: One-line npx installation, no complex configuration needed
- **Production Ready**: Comprehensive error handling, TypeScript types, and extensive documentation
- **Active Development**: Regular updates with new Gemini features as they're released
## Documentation
- **[Usage Guide](USAGE_GUIDE.md)** - Complete guide on using all tools and features
- **[Parameters Reference](PARAMETERS_REFERENCE.md)** - Detailed documentation of all parameters
- **[Quick Reference](QUICK_REFERENCE.md)** - Quick commands cheat sheet
- **[Enhanced Features](ENHANCED_FEATURES.md)** - Detailed list of v4.0.0 capabilities
- [Claude Desktop Setup Guide](docs/claude-desktop-setup.md) - Detailed setup instructions
- [Examples and Usage](docs/examples.md) - Usage examples and advanced configuration
- [Implementation Notes](docs/implementation-notes.md) - Technical implementation details
- [Development Guide](docs/development-guide.md) - Guide for developers
- [Troubleshooting Guide](docs/troubleshooting.md) - Common issues and solutions
## Local Development
```bash
# Clone repository
git clone https://github.com/aliargun/mcp-server-gemini.git
cd mcp-server-gemini
# Install dependencies
npm install
# Set up environment variables
cp .env.example .env
# Edit .env and add your GEMINI_API_KEY
# Start development server
npm run dev
```
## Contributing
Contributions are welcome! Please see our [Contributing Guide](CONTRIBUTING.md).
## Common Issues
1. **Connection Issues**
- Ensure your MCP client is properly restarted
- Check the client's logs (e.g., `~/Library/Logs/Claude/mcp-server-gemini.log` for Claude Desktop on Mac)
- Verify internet connection
- See [Troubleshooting Guide](docs/troubleshooting.md)
2. **API Key Problems**
- Verify API key is correct
- Check API key has proper permissions
- Ensure the key is set in the environment variable
- See [Setup Guide](docs/claude-desktop-setup.md)
## Security
- API keys are handled via environment variables only
- Never commit API keys to version control
- The `.claude/` directory is excluded from git
- No sensitive data is logged or stored
- Regular security updates
- If your API key is exposed, regenerate it immediately in Google Cloud Console
## License
MIT
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: image analysis, token counting, text embedding, text generation, help retrieval, and model listing. The descriptions reinforce these distinct functions, making tool selection unambiguous for an agent.
All tool names follow a consistent verb_noun pattern (e.g., analyze_image, count_tokens, embed_text), using snake_case throughout. This predictable naming scheme enhances readability and usability for agents.
With 6 tools, the server is well-scoped for its purpose of providing Gemini AI capabilities. Each tool serves a specific, essential function (e.g., core generation, analysis, and utility tasks), with no redundant or trivial additions.
The tool set covers key Gemini functionalities like text generation, image analysis, embeddings, and model listing, with a helpful utility tool. A minor gap is the lack of tools for managing conversations or multi-turn interactions, but core workflows are well-supported.