Provides access to Google's Gemini Pro API for text generation and image analysis using Gemini Pro Vision capabilities
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Gemini Pro MCP Server generate a summary of quantum computing basics"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for integrating Gemini Pro API with Claude Desktop.
Install dependencies:
npm installGet your Gemini API key:
Go to Google AI Studio
Create a new API key
Copy the key
Set up environment variable:
export GEMINI_API_KEY="your-api-key-here"Build the project:
npm run buildConfigure Claude Desktop:
Edit your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
Add this configuration:
{
"mcpServers": {
"gemini-pro": {
"command": "node",
"args": ["/Users/luis_ticas/Documents/gemini-mcp-server/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-gemini-api-key-here"
}
}
}
}Restart Claude Desktop
Related MCP server: MCP Gemini Server
generate_text: Generate text using Gemini Pro
analyze_image: Analyze images using Gemini Pro Vision
Once connected, you can use commands like:
"Generate text using Gemini about [topic]"
"Analyze this image using Gemini"
Analyze an image using Gemini 2.5 Pro Vision
Inputs: imageData (required), prompt.
Generate text using Gemini 2.5 Pro model
Inputs: prompt (required), maxTokens, temperature.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have completely distinct purposes: one analyzes images and the other generates text. There is no overlap in functionality, making it impossible to confuse them.
Both tools follow a consistent verb_noun pattern (analyze_image, generate_text) with clear, descriptive names that indicate their specific actions and targets.
With only two tools, the server feels under-scoped for a Gemini Pro MCP Server, which might be expected to offer more capabilities like editing, summarizing, or multimodal interactions beyond basic image analysis and text generation.
The toolset is severely incomplete for a Gemini Pro server, lacking essential operations such as editing text, summarizing content, handling multimodal inputs beyond images, or providing model configuration options, which limits agent workflows.
Generate images and video from Claude with one API key.
Generate and edit images and create short videos inside Claude. Prepaid credits, no subscription.
Multiple Google accounts (Gmail, Calendar, Drive, Contacts, Tasks) in one Claude connector.
Multiple Google accounts (Gmail, Calendar, Drive, Contacts, Tasks) in one Claude connector.
