mcp-think-tool

MCP.Pizza Chef: DannyMac180

The mcp-think-tool is an MCP server that implements the 'think' tool to enhance Claude's complex reasoning by providing a structured space for breaking down problems, maintaining a timestamped thought history, and offering analysis of thinking patterns. It supports clearing thought history for fresh starts, improving multi-step reasoning and policy adherence in long tool call chains.

Use This MCP server To

Enable Claude to perform structured multi-step reasoning Maintain timestamped logs of AI thought processes Analyze AI thinking patterns for debugging or optimization Clear thought history to reset reasoning context Improve policy adherence in complex AI workflows

README

MCP Think Tool Server

A Model Context Protocol (MCP) server implementing the "think" tool for improving Claude's complex reasoning capabilities.

Overview

This MCP server implements the "think" tool as described in Anthropic's blog post, which provides Claude with a dedicated space for structured thinking during complex problem-solving tasks. The think tool has been shown to significantly improve performance in complex tasks requiring policy adherence and reasoning in long chains of tool calls.

Features

  • Structured Thinking Space: Provides Claude with a dedicated place to break down complex problems
  • Thought History: Maintains a log of all thoughts with timestamps for reference
  • Statistics and Analysis: Offers metadata about thinking patterns
  • Clean Slate Option: Allows clearing thought history when starting fresh

Installation

Install from PyPI:

pip install mcp-think-tool

Configuration

Windsurf

To use this tool with Claude in Windsurf, add the following configuration to your MCP config file:

"think": {
    "command": "/home/xxx/.local/bin/mcp-think-tool",
    "args": [],
    "type": "stdio",
    "pollingInterval": 30000,
    "startupTimeout": 30000,
    "restartOnFailure": true
}

The command field should point to the directory where you installed the python package using pip.

Docker

You can install this MCP server with only the Dockerfile

First download the Dockerfile, navigate to its directory, and build the Docker image

docker build -t mcp-think-tool .

Then add the following configuration your MCP config file

"think": {
    "command": "docker",
    "args": ["run", "--rm", "-i", "mcp-think-tool"]
}

This was tested and working with Claude Desktop and Cursor

mcp-think-tool FAQ

How do I install the mcp-think-tool server?
You can install it easily via PyPI using 'pip install mcp-think-tool'.
What is the purpose of the thought history in the think tool?
It maintains a timestamped log of all thoughts to help track and reference the AI's reasoning process.
Can I clear the thought history during a session?
Yes, the think tool provides a clean slate option to reset the thought history when needed.
How does the think tool improve Claude's reasoning?
By providing a dedicated structured space for breaking down complex problems and maintaining thought logs, it enhances multi-step reasoning and policy adherence.
Is the think tool specific to Claude or usable with other LLMs?
While designed for Claude, the think tool concept can be adapted for other LLMs like OpenAI's GPT-4 and Anthropic's Claude.
Does the think tool provide any analytics?
Yes, it offers statistics and metadata about thinking patterns to help analyze AI behavior.
Can the think tool be integrated into existing MCP workflows?
Yes, it is designed as an MCP server to plug into MCP clients and workflows seamlessly.
What programming languages or environments support the mcp-think-tool?
It is a Python package installable via PyPI, suitable for Python-based MCP environments.