Think MCP server

Think MCP provides a structured reasoning tool for agentic AI workflows, implementing the MCP (Model Context Protocol) server. It adds a "think" tool that allows AI agents to pause and record explicit thoughts during complex reasoning tasks, helping them process information, backtrack, or comply with detailed policies - without changing the environment or database.

Installation

To use Think MCP, you'll need to install it using the uvx package manager. First, make sure you have uvx installed on your system.

pip install uvx

Then you can install the Think MCP tool:

uvx install think-mcp

Basic Configuration

To integrate the Think MCP server into your agent, add the following configuration:

"mcpServers": {
    "think-mcp": {
        "command": "uvx",
        "args": ["think-mcp"],
        "enabled": true
    }
}

Using the Think Tool

The "think" tool allows an AI agent to pause and record explicit thoughts during complex reasoning or multi-step tool use.

Tool Definition

• Input: thought (string) — A thought to think about
• Behavior: Appends the thought to the log for structured reasoning

This approach is especially useful for:

• Tool output analysis (processing results of previous tool calls)
• Policy-heavy environments (verifying compliance with guidelines)
• Sequential decision making (where each step builds on previous ones)

Advanced Mode

Think MCP also offers an advanced mode that provides additional cognitive tools for your agent:

• criticize
• plan
• search

Configuring Advanced Mode

To enable advanced mode, update your configuration as follows:

"mcpServers": {
    "think-mcp": {
        "command": "uvx",
        "args": ["think-mcp", "--advanced"],
        "enabled": true,
        "env": {
            "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY_HERE"
        }
    }
}

Note that the advanced mode with search functionality requires a Tavily API key.

Benefits

According to Anthropic's research, adding the think tool can lead to improved evaluation metrics by enabling reasoning capabilities even in models that do not natively possess advanced reasoning skills.

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.