Sequential Thinking MCP server

Provides a flexible sequential thinking tool powered by Gemini, enabling step-by-step problem analysis and reasoning through dynamic thought generation and session tracking for developers and workflow optimization.
Back to servers
Provider
Chong U
Release date
Mar 26, 2025
Language
TypeScript
Stats
1 star

This MCP server implementation allows you to leverage Google's Gemini AI models through Claude or other MCP clients by providing a compatible protocol interface. It fully supports the Model Context Protocol with SSE transport and integrates with Gemini 1.5 Pro.

Installation Options

Deploying on Smithery AI

The easiest way to use this server is by deploying it on Smithery AI:

  1. Create an account on Smithery AI if you don't have one
  2. Deploy the Gemini MCP Server project
  3. Configure the required environment variable:
    • GEMINI_API_KEY: Your Google AI Studio API key for accessing Gemini models

Running Locally

If you prefer to run the server on your own machine:

# Clone the repository
git clone [repository-url]

# Install dependencies
npm install

# Set your Gemini API key
export GEMINI_API_KEY=your_key_here

# Start the server
npm start

Connecting to the Server

Once your server is running (either on Smithery AI or locally), you can connect to it from any MCP client:

Using with Claude Desktop

  1. Copy the URL where your server is running:

    • For Smithery AI: Use the deployment URL provided
    • For local installation: Typically http://localhost:3000 (or whatever port configured)
  2. In Claude Desktop:

    • Go to Settings > MCP Servers
    • Add a new server with:
      • Name: Gemini MCP
      • URL: Your server URL
    • Save the settings
    • Restart Claude

Using with Other MCP Clients

For other MCP-compatible clients, follow the client's specific instructions for adding custom model servers, using your Gemini MCP server URL.

Features Available

When connected, you'll have access to:

  • Gemini 1.5 Pro model capabilities
  • Sequential thinking tool implementation
  • Full MCP protocol support through SSE transport

The server is configured via environment variables, making it easy to adjust settings as needed.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later