Log inSubmit server
Think MCP logo

Think MCP

by Rai220

Provides a 'think' tool MCP server for AI agents to record explicit reasoning steps during complex workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Think MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "rai220-think-mcp": {
      "command": "uvx",
      "args": [
        "think-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

This MCP server implements the 'think' tool from Anthropic's research, enabling AI agents to pause and log explicit thoughts during multi-step reasoning or tool use. It helps agents process information, backtrack, and comply with detailed policies without altering the environment or database. The server supports integration with agentic LLMs like Claude and offers an advanced mode with additional reasoning tools.

Use cases

  • Record intermediate reasoning steps in multi-tool workflows
  • Analyze outputs from previous tool calls
  • Enforce compliance in policy-heavy environments
  • Support sequential decision making with explicit thought logs

Key features

  • Implements Anthropic's 'think' tool for structured reasoning
  • Minimal, standards-based MCP server using mcp[cli]
  • Appends thoughts to logs without changing environment state
  • Advanced mode adds criticize, plan, and search tools

Tools1

What Think MCP lets your agent do. Expand a tool for its parameters.

Self-reported~2 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

20/21 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 11d ago via OSV.dev · think-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars107Stargazers on the source repository.
Last commit7mo agoMost recent push to the default branch.
Tools exposed1Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

From the project README

Think MCP Tool

Think MCP is an implementation of an MCP (Model Context Protocol) server that provides a "think" tool for structured reasoning in agentic AI workflows. This project is inspired by the Anthropic engineering article: The "think" tool: Enabling Claude to stop and think in complex tool use situations.

According to the referenced article, 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.

alt text

Think Tool MCP server

What is the "think" tool?

The "think" tool allows an AI agent to pause and record an explicit thought during complex reasoning or multi-step tool use. It does not change the environment or database, but appends the thought to the log, helping the agent process information, backtrack, or comply with detailed policies.

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)

Features

  • Implements the "think" tool as described in Anthropic's research
  • Minimal, standards-based MCP server using mcp[cli]
  • Ready for integration with Claude or other agentic LLMs

Usage

MCP server configuration

Add this MCP server to your facorite agent.

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

Tool definition

The "think" tool is defined as:

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

Advanced mode

Adds aditional tools for your agent:

  • criticize
  • plan
  • search
Code
"mcpServers": {
    "think-mcp": {
        "command": "uvx",
        "args": ["think-mcp", "--advanced"],
        "enabled": true,
        "env": {
            "TAVILY_API_KEY": ... YOUR TAVILY API KEY HERE ...
        }
    }
}

Reference

License

MIT License — see LICENSE

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Think MCP

It accepts a single string input called 'thought' which is appended to the agent's reasoning log.

No, it only appends the provided thought to the log without changing the environment or database.

Advanced mode adds 'criticize', 'plan', and 'search' tools for enhanced agent capabilities.

Add the server under 'mcpServers' with the command 'uvx' and args ['think-mcp'], enabling it as shown in the README.

Yes, advanced mode requires setting the TAVILY_API_KEY environment variable.

Related MCP servers

All in Other Tools and Integrations All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewThink MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/rai220-think-mcp?style=directory)](https://allmcps.com/mcp/rai220-think-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/rai220-think-mcp"><img src="https://allmcps.com/api/badge/rai220-think-mcp?style=directory" alt="Think MCP on AllMCPs" /></a>