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.

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.
"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
"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
Recommend MCP Servers 💡
@billster45/mcp-chatgpt-responses
MCP server for access to OpenAI's ChatGPT API with Responses API for conversation management
bounteous-hulk
A Model Context Protocol (MCP) server implementation enabling integration between LLM applications and GitHub/GitLab version control systems
@crunchloop/mcp-teamtailor
An MCP server integrating with the Teamtailor API to manage candidates and provide recruitment context.
fitbit-mcp
MCP implementation for Fitbit to enable AI assistants access to health and fitness data
@gannonh/memento-mcp
A scalable, high-performance knowledge graph memory system for LLMs with semantic retrieval, contextual recall, and temporal awareness, using Neo4j as its storage backend.
@tacticlaunch/mcp-linear
MCP server that enables AI assistants to interact with Linear project management system through natural language, allowing users to retrieve, create, and update issues, projects, and teams.