MCP Think Tool Server
An MCP server implementing the 'think' tool to improve Claude's complex reasoning capabilities.
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 Anthropic's "think" tool, which provides Claude with a dedicated space for structured thinking during complex problem-solving tasks. As described in Anthropic's blog post, the think tool has been shown to significantly improve performance in complex tasks requiring policy adherence and reasoning in long chains of tool calls.
Custom Instructions
Add these custom instructions to Claude to optimize its use of the think tool:
You have access to a "think" tool that provides a dedicated space for structured reasoning. Using this tool significantly improves your performance on complex tasks.
## When to use the think tool
Before taking any action or responding to the user after receiving tool results, use the think tool as a scratchpad to:
- List the specific rules that apply to the current request
- Check if all required information is collected
- Verify that the planned action complies with all policies
- Iterate over tool results for correctness
- Analyze complex information from web searches or other tools
- Plan multi-step approaches before executing them
## How to use the think tool effectively
When using the think tool:
1. Break down complex problems into clearly defined steps
2. Identify key facts, constraints, and requirements
3. Check for gaps in information and plan how to fill them
4. Evaluate multiple approaches before choosing one
5. Verify your reasoning for logical errors or biases
Key Use Cases
- Complex Tool Chains: When Claude needs to call complex tools and analyze outputs carefully
- Policy Adherence: For navigating policy-heavy environments with detailed guidelines
- Sequential Decision Making: When each step builds on previous ones and mistakes are costly
- Multi-step Analysis: Breaking down complex problems into manageable steps
Installation
Installing via Smithery
To install Think Tool Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @cgize/claude-mcp-think-tool --client claude
Manual Installation
npm install -g @cgize/mcp-think-tool
Configuration
Add this configuration to your MCP configuration file:
{
"mcpServers": {
"think-tool": {
"command": "npx",
"args": [
"-y",
"@cgize/mcp-think-tool"
],
"type": "stdio",
"pollingInterval": 30000,
"startupTimeout": 30000,
"restartOnFailure": true
}
}
}
Configuration file location:
C:\Users\[username]\AppData\Roaming\Claude\claude_desktop_config.json
If installed globally, you can also use:
{
"mcpServers": {
"think-tool": {
"command": "claude-mcp-think-tool",
"args": [],
"type": "stdio",
"pollingInterval": 30000,
"startupTimeout": 30000,
"restartOnFailure": true
}
}
}
Available Tools
- think: Record structured reasoning during problem-solving
- get_thoughts: Retrieve all recorded thoughts
- clear_thoughts: Reset the thinking process
- get_thought_stats: Analyze thinking patterns
Example Prompt
Using the think tool, solve this multi-step problem:
A train travels at a constant speed of 60 km/h. It departs from station A at 9:00 AM and arrives at station B at 11:30 AM. What is the distance between stations A and B?
License
MIT
Servidores relacionados
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Code Summarizer
A command-line tool that summarizes code files in a directory using Gemini Flash 2.0.
Postman MCP Server
Run Postman collections using Newman, with support for environment and global variables.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)
ABP.IO MCP Server
An MCP server for ABP.IO that enables AI models to interact with your ABP applications and framework.
IndAutomation MCP Server
AI-powered industrial fault diagnosis MCP server. 313 fault codes across Allen-Bradley, Siemens, ABB, Mitsubishi, Fanuc. 8 diagnostic tools for Claude Code.
MegaChad
Burn-to-create looksmaxxing engine on MegaETH with 14 MCP tools for swap quotes, token stats, NFT minting, gallery, leaderboard, wallet checks, gasless burns, and orchestrated agent flows
Pollinations MCP Server
Generate images and text using the Pollinations.ai API.
1MCP
A unified MCP server that aggregates multiple MCP servers into a single endpoint.
Algorand
A comprehensive MCP server for tooling interactions(40+) and resource accessibility(60+) plus many useful prompts to interact with Algorand Blockchain.
MKP
Model Kontext Protocol Server for Kubernetes that allows LLM-powered applications to interact with Kubernetes clusters through native Go implementation with direct API integration and comprehensive resource management.