claude mcp think tool
Implements Anthropic's 'think' tool for Claude, providing a dedicated space for structured reasoning during complex problem-solving tasks that improves performance in reasoning chains and policy adherence.
Implements Anthropic's 'think' tool for Claude, providing a dedicated space for structured reasoning during complex problem-solving tasks that improves performance in reasoning chains and policy adherence.
A Model Context Protocol (MCP) server implementing the "think" tool for improving Claude's complex reasoning capabilities.
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.
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
npm install -g @cgize/mcp-think-tool
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]AppDataRoamingClaudeclaude_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
}
}
}
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?
MIT
[
{
"description": "Use this tool to think about something. It will not obtain new information or change anything, but just append the thought to the log. Use it when complex reasoning or cache memory is needed, especially during long chains of tool calls, policy adherence scenarios, or sequential decision making.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"thought": {
"description": "A thought to think about. This can be structured reasoning, step-by-step analysis, policy verification, or any other mental process that helps with problem-solving.",
"type": "string"
}
},
"required": [
"thought"
],
"type": "object"
},
"name": "think"
},
{
"description": "Retrieve all thoughts recorded in the current session to review your reasoning process.",
"inputSchema": {
"type": "object"
},
"name": "get_thoughts"
},
{
"description": "Clear all thoughts recorded in the current session. Use this to start fresh if the thinking process needs to be reset.",
"inputSchema": {
"type": "object"
},
"name": "clear_thoughts"
},
{
"description": "Get statistics about the thoughts recorded in the current session to analyze your thinking process.",
"inputSchema": {
"type": "object"
},
"name": "get_thought_stats"
}
]