Think MCP
Created 5 months ago
Think MCP is an implementation of an MCP server providing a 'think' tool for structured reasoning in AI workflows.
What is Think MCP?
Enhances any agent's reasoning capabilities by integrating the think-tools, as described in [Anthropic's article](https://www.anthropic.com/engineering/claude-think-tool).
Documentation
Think MCP Tool
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.
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 favorite 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 additional 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
Server Config
{
"mcpServers": {
"think-mcp-server": {
"command": "npx",
"args": [
"think-mcp"
]
}
}
}