Enhances any agent's reasoning capabilities by integrating the think-tools, as described in Anthropic's article.
Add to Claude Desktop config.json
{
"mcpServers": {
"rai220-think-mcp": {
"command": "python",
"args": [
"-m",
"think_mcp"
]
}
}
} Get the source and run locally
git clone https://github.com/Rai220/think-mcp.git ~/.mcp/think-mcp
cd ~/.mcp/think-mcp 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.

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:
Add this MCP server to your facorite agent.
"mcpServers": {
"think-mcp": {
"command": "uvx",
"args": ["think-mcp"],
"enabled": true
}
}
The “think” tool is defined as:
thought (string) — A thought to think about.Adds aditional tools for your agent:
"mcpServers": {
"think-mcp": {
"command": "uvx",
"args": ["think-mcp", "--advanced"],
"enabled": true,
"env": {
"TAVILY_API_KEY": ... YOUR TAVILY API KEY HERE ...
}
}
}
MIT License — see LICENSE
MCP server that exercises all the features of the MCP protocol.
A high-level framework for building MCP servers in Python
Local-first system capturing screen/audio with timestamped indexing, SQL/embedding storage, semantic search, LLM-powered history analysis, and event-triggered actions - enables building context-aware AI agents through a NextJS plugin ecosystem.
Extract and convert YouTube video information.
Interacting with Obsidian via REST API
Connect AI agents to 600+ integrations with a single interface - OAuth, scaling, and monitoring included