Package Exports

@mseep/gemini-sequential-thinking-mcp
@mseep/gemini-sequential-thinking-mcp/server/server-direct.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@mseep/gemini-sequential-thinking-mcp) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Gemini MCP Server

An MCP (Model Context Protocol) server implementation that enables using Google's Gemini AI models through Claude or other MCP clients.

Features

Full MCP protocol support via SSE transport
Gemini 1.5 Pro model integration
Sequential thinking tool implementation
Environment variable configuration

Deployment on Smithery AI

This server is designed to be easily deployed on Smithery AI. Once deployed, you'll be able to connect to it from any MCP client like Claude.

Configuration

The server requires the following environment variables:

GEMINI_API_KEY: Your Google AI Studio API key for accessing Gemini models

Local Development

If you want to run this server locally:

Clone the repository
Install dependencies: npm install
Set your Gemini API key: export GEMINI_API_KEY=your_key_here
Start the server: npm start

How to Use

After deploying to Smithery AI, you'll get a unique URL that you can add to your MCP client:

Copy the deployment URL from Smithery AI
In Claude Desktop, go to Settings > MCP Servers
Add a new server with:
- Name: Gemini MCP
- URL: Your Smithery deployment URL
Save and restart Claude

License

MIT