MCP cover image
See in Github
2025-01-08

A systematic reasoning MCP server implementation for Claude Desktop with beam search and thought evaluation.

1

Github Watches

19

Github Forks

162

Github Stars

MCP Reasoner

A reasoning implementation for Claude Desktop that lets you use both Beam Search and Monte Carlo Tree Search (MCTS). tbh this started as a way to see if we could make Claude even better at complex problem-solving... turns out we definitely can.

Current Version:

v2.0.0

What's New:

Added 2 Experimental Reasoning Algorithms:

- `mcts-002-alpha`

    - Uses the A* Search Method along with an early *alpha* implementation of a Policy Simulation Layer

    - Also includes an early *alpha* implementation of Adaptive Exploration Simulator & Outcome Based Reasoning Simulator

*NOTE* the implementation of these alpha simulators is not complete and is subject to change

- `mcts-002alt-alpha`

    - Uses the Bidirectional Search Method along with an early *alpha* implementation of a Policy Simulation Layer

    - Also includes an early *alpha* implementation of Adaptive Exploration Simulator & Outcome Based Reasoning Simulator

*NOTE* the implementation of these alpha simulators is not complete and is subject to change

What happened to mcts-001-alpha and mcts-001alt-alpha?

Quite simply: It was useless and near similar to the base mcts method. After initial testing the results yielded in basic thought processes was near similar showing that simply adding policy simulation may not have an effect.

So why add Polciy Simulation Layer now?

Well i think its important to incorporate Policy AND Search in tandem as that is how most of the algorithms implement them.

Previous Versions:

v1.1.0

Added model control over search parameters:

beamWidth - lets Claude adjust how many paths to track (1-10)

numSimulations - fine-tune MCTS simulation count (1-150)

Features

  • Two search strategies that you can switch between:
    • Beam search (good for straightforward stuff)
    • MCTS (when stuff gets complex) with alpha variations (see above)
  • Tracks how good different reasoning paths are
  • Maps out all the different ways Claude thinks through problems
  • Analyzes how the reasoning process went
  • Follows the MCP protocol (obviously)

Installation

git clone https://github.com/frgmt0/mcp-reasoner.git 

OR clone the original:

git clone https://github.com/Jacck/mcp-reasoner.git

cd mcp-reasoner
npm install
npm run build

Configuration

Add to Claude Desktop config:

{
  "mcpServers": {
    "mcp-reasoner": {
      "command": "node",
      "args": ["path/to/mcp-reasoner/dist/index.js"],
    }
  }
}

Testing

[More Testing Coming Soon]

Benchmarks

[Benchmarking will be added soon]

Key Benchmarks to test against:

  • MATH500

  • GPQA-Diamond

  • GMSK8

  • Maybe Polyglot &/or SWE-Bench

License

This project is licensed under the MIT License - see the LICENSE file for details.

相关推荐

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • Lists Tailwind CSS classes in monospaced font

  • https://zenepic.net
  • Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.

  • https://appia.in
  • Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease

  • Mintplex-Labs
  • The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

  • ravitemer
  • A powerful Neovim plugin for managing MCP (Model Context Protocol) servers

  • jae-jae
  • MCP server for fetch web page content using Playwright headless browser.

  • patruff
  • Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

  • pontusab
  • The Cursor & Windsurf community, find rules and MCPs

  • n8n-io
  • Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

  • WangRongsheng
  • 🧑‍🚀 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.

  • metorial
  • Containerized versions of hundreds of MCP servers 📡 🧠

  • av
  • Effortlessly run LLM backends, APIs, frontends, and services with one command.

  • langgenius
  • Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

    Reviews

    1 (1)
    Avatar
    user_StQxHpJ1
    2025-04-17

    The mcp-reasoner by Jacck is an outstanding tool for reasoning and decision-making processes. The functionality and ease of use are impressive, catering to both novices and experts in the field. The documentation on the GitHub page is clear and detailed, making it simple to get started. Highly recommended for anyone needing a powerful reasoning application!