@mcpflow.io/mcp-mcp-reasoner

# MCP Reasoner  > 此包由 [MCPFlow](https://mcpflow.io) 打包并发布到npm仓库。为Claude Desktop 实现的基于系统推理的MCP服务器，采用波束搜索和思维评估。 ## 安装与使用直接使用npx运行: ```bash npx @mcpflow.io/mcp-mcp-reasoner ``` 或者先安装后使用: ```bash # 安装 npm install @mcpflow.io/mcp-mcp-reasoner # 使用 npx @mcpflow.io/mcp-mcp-reasoner ``` ## 使用方法 ## 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 ``` ## 工具函数 ### processInput 处理输入并确保正确的类型 **参数:** - `input`: 输入数据 ### registerTheTool 注册工具 **参数:** ### handleRequests 处理请求 **参数:** - `request`: 请求对象 ### processThought 使用选定的策略处理思想 **参数:** - `request`: 处理请求 ### getStats 获取推理统计信息 **参数:** ### getStrategyMetrics 获取策略度量 **参数:** ### getCurrentStrategyName 获取当前策略名称 **参数:** ### getBestPath 获取最佳路径 **参数:** ### clear 清除状态 **参数:** ### setStrategy 设置策略 **参数:** - `beamWidth`: 束宽 - `strategyType`: 策略类型 - `numSimulations`: 模拟次数 ### getAvailableStrategies 获取可用策略 **参数:** ### processThought 处理思想 **参数:** - `request`: 请求 ### getBestPath 获取最佳路径 **参数:** ### clear 清除 **参数:** ### getMetrics 获取度量 **参数:** ### clear 清除 **参数:** ### processThought 处理思想 **参数:** - `request`: 请求 ### getBestPath 获取最佳路径 **参数:** ### clear 清除 **参数:** ### getMetrics 获取度量 **参数:** ### clear 清除 **参数:** ### processThought 处理思想 **参数:** - `request`: 请求 ### getBestPath 获取最佳路径 **参数:** ### clear 清除 **参数:** ### getMetrics 获取度量 **参数:** ### clear 清除 **参数:** ## 原始信息 - **开发者:** Jacck - **版本:** 1.0.0 - **许可证:** MIT License - **原始仓库:** [Jacck/mcp-reasoner](https://github.com/Jacck/mcp-reasoner) ## 原始README # 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](LICENSE) file for details.