Gemini MCP server

The Gemini MCP Server provides seamless access to Google's latest Gemini AI models directly in your development environment. Through Model Context Protocol (MCP) integration, you can use Gemini's powerful features including text generation, image analysis, and embeddings without leaving your favorite editor.

Installation

Prerequisites

You need a Gemini API key to use this server:

1. Visit Google AI Studio
2. Create a new API key
3. Keep your API key secure and never commit it to version control

Setup with MCP Clients

Claude Desktop

Edit your Claude Desktop configuration file:

• Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "gemini": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "github:aliargun/mcp-server-gemini"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Cursor

Add to Cursor's MCP settings:

{
  "gemini": {
    "type": "stdio",
    "command": "npx",
    "args": ["-y", "github:aliargun/mcp-server-gemini"],
    "env": {
      "GEMINI_API_KEY": "your_api_key_here"
    }
  }
}

Other MCP Clients

Use the standard MCP stdio configuration:

{
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "github:aliargun/mcp-server-gemini"],
  "env": {
    "GEMINI_API_KEY": "your_api_key_here"
  }
}

After configuration, restart your MCP client to apply the changes.

Usage

Available Models

Model	Context	Features	Best For
gemini-2.5-pro	2M tokens	Thinking, JSON, Grounding	Complex reasoning
gemini-2.5-flash	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

Basic Commands

You can use natural language in your MCP client to access Gemini's capabilities:

"Use Gemini to explain quantum computing"
"Analyze this image with Gemini" 
"List all Gemini models"
"Get help on using Gemini"

Advanced Examples

For more control over the model parameters:

"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"

Troubleshooting

Connection Issues

If you experience connection problems:

• 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 your internet connection

API Key Problems

If you have issues with your API key:

• Verify the API key is correct
• Check that the API key has proper permissions
• Ensure the key is correctly set in the environment variable
• If your API key is exposed, regenerate it immediately in Google Cloud Console

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "gemini" '{"command":"npx","args":["-y","github:aliargun/mcp-server-gemini"],"env":{"GEMINI_API_KEY":"your_api_key_here"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "gemini": {
            "command": "npx",
            "args": [
                "-y",
                "github:aliargun/mcp-server-gemini"
            ],
            "env": {
                "GEMINI_API_KEY": "your_api_key_here"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "gemini": {
            "command": "npx",
            "args": [
                "-y",
                "github:aliargun/mcp-server-gemini"
            ],
            "env": {
                "GEMINI_API_KEY": "your_api_key_here"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect