
mcp-thinking
thinking tool for claude desktop/mcp clients using Deepseek reasoner
2
Github Watches
4
Github Forks
51
Github Stars
MCP Thinking Server
Extract the thinking chain of thought of the Deepseek R1 reasoning model and use it in Claude Desktop or any MCP client.
Setup
To install dependencies:
bun install
Run the setup script to create the MCP config file. You will need to input your Deepseek API key:
bun setup
Open Claude Desktop and enjoy reasoning with Deepseek R1.
Tests
copy .env.test.example
to .env.test
.
cp .env.test.example .env.test
Run the tests:
bun test
Credits
Thanks to @jacksteamdev's awesome repo for the example of MCP in bun. The setup script and logger are "heavily" inspired by it.
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Emulating Dr. Jordan B. Peterson's style in providing life advice and insights.
Your go-to expert in the Rust ecosystem, specializing in precise code interpretation, up-to-date crate version checking, and in-depth source code analysis. I offer accurate, context-aware insights for all your Rust programming questions.
Advanced software engineer GPT that excels through nailing the basics.
Converts Figma frames into front-end code for various mobile frameworks.
Take an adjectivised noun, and create images making it progressively more adjective!
Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
🧑🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.
Reviews

user_qTonoFG4
As a dedicated user of mcp-thinking, I can confidently say that this tool by mattzcarey is a game-changer. It provides an intuitive and efficient platform for anyone looking to enhance their problem-solving skills. Highly recommend checking it out at https://github.com/mattzcarey/mcp-thinking!