AM

azdeltaqq/mcp-reasoning-server

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

13 stars 6 forks 质量 52 趋势 20

这是一个非常基本的执行.

概览

一个模式背景协议(MCP)服务器,在Cursor AI中为克洛德提供先进的推理能力. - 使用MCTS推理完成复杂的解决问题任务。 - 探索多条推理路径。 - 利用变形器对复杂问题的推理。 - 将变形器分析与MCTS结合起来,以加强推理。 - 说吧 所有多步推理方法都会在一个工具调用中自动完成所有推理步骤. 2. 打开光标 AI 3. 导航到设置 > 特性 > MCP 4. 点击 " + 新增全局MCP服务器"按钮 5. 输入以下细节 : - 在命令字段中: 节点 C:\ Users\[您的用户名]\path\to\mcp- reasoning-server\dist\index.js - 确保使用您工程的 dist/index.js 文件的全部路径 - 对 Windows 路径 6 使用双回鞭. 点击"Add" 7. 在列表中查找您的服务器( 它将初始显示为“ 残疾 ) 8. 点击"Disabled"将其切换为"Enabled" 9. 点击刷新按钮来装入可用的工具 10 .

概述(AI 翻译)

值得注意的是:

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

谢谢你给我这个想法杰克。

光标AI的 MCP 高级理性服务器

一个模式背景协议(MCP)服务器,在Cursor AI中为克洛德提供先进的推理能力.

□ 特性

  • 蒙特·卡洛树搜索(MCTS): 在复杂的解决问题任务中使用MCTS推理.
  • ** Beam Search**:同时探索多条推理路径.
  • R1变形器:利用变形器对复杂问题的推理.
  • Hybrid Reasoning:将变形器分析与MCTS结合,以加强推理.
  • ** 自动 – – 异常原因**: 所有多步推理方法都会在一个工具调用中自动完成所有推理步骤.

□ 安装

□ 使用量

配置 Cursor AI

  1. 首先构建服务器:

  2. 打开光标AI

  3. 导航到设置 > 特性 > MCP

  4. 点击 " + 添加全局 MCP 服务器按钮

  5. 输入下列细节:

  • 在指挥领域:node C:\\Users\\[YourUsername]\\path\\to\\mcp-reasoning-server\\dist\\index.js
  • 确保使用您的项目 dist/index.js 文件的全部路径
  • 对Windows路径使用双回鞭
  1. 点击"Add"
  2. 联合国.

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

Notable Mentions :

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

Thanks for giving me the idea Jacck .

MCP Advanced Reasoning Server for Cursor AI

A Model Context Protocol (MCP) server that provides advanced reasoning capabilities for Claude in Cursor AI.

Features

  • Monte Carlo Tree Search (MCTS): Use MCTS reasoning for complex problem-solving tasks.
  • Beam Search: Explore multiple reasoning paths simultaneously.
  • R1 Transformer: Leverage Transformer-based reasoning for complex problems.
  • Hybrid Reasoning: Combine Transformer analysis with MCTS for enhanced reasoning.
  • Auto-Iterative Reasoning: All multi-step reasoning methods automatically complete all reasoning steps in a single tool call.

Installation

npm install
npm run build

Usage

Configuring with Cursor AI

  1. Build the server first:

    cd mcp-reasoning-server
    npm run build
    
  2. Open Cursor AI

  3. Navigate to Settings > Features > MCP

  4. Click the “+ Add new global MCP server” button

  5. Enter the following details:

    • In the command field: node C:\\Users\\[YourUsername]\\path\\to\\mcp-reasoning-server\\dist\\index.js
    • Make sure to use the full path to your project’s dist/index.js file
    • Use double backslashes for Windows paths
  6. Click “Add”

  7. Find your server in the list (it will initially show as “Disabled”)

  8. Click “Disabled” to toggle it to “Enabled”

  9. Click the refresh button to load the available tools

  10. A command prompt window will open automatically - this is your server running

  11. As long as this command prompt window remains open, the reasoning tools will be available

Alternatively, you can manually edit your Cursor MCP configuration file at C:\Users\[Username]\.cursor\mcp.json (Windows):

{
  "mcpServers": {
    "mcp-reasoner": {
      "command": "node",
      "args": ["C:\\Users\\[Username]\\path\\to\\mcp-reasoning-server\\dist\\index.js"]
    }
  }
}

Important Notes

  • Server Running: The tools are only available while the command prompt window is open and running
  • Making Changes: If you make changes to the server code, you must rebuild it with npm run build before restarting
  • Restarting: To restart the server, close the command prompt window and toggle the server off/on in Cursor Settings

Using the Reasoning Tools

You can use the reasoning tools directly in your Cursor AI conversations with Claude:

MCTS Reasoning

Use the /reason-mcts command followed by your query to start a MCTS-based reasoning chain:

/reason-mcts How can I optimize the performance of this React component?

Beam Search Reasoning

Use the /reason-beam command for beam search-based reasoning:

/reason-beam What architecture would be best for this microservice system?

R1 Transformer Reasoning

Use the /reason-r1 command for single-step Transformer-based reasoning:

/reason-r1 Analyze the complexity of this algorithm.
在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "mcp-reasoner": { "command": "node", "args": ["C:\\Users\\[Username]\\path\\to\\mcp-reasoning-server\\dist\\index.js"] } } }