MCTS MCP Server

](https://mseep.ai/app/angrysky56-mcts-mcp-server)

MCTS MCP服务器

一种模型上下文协议（MCP）服务器，它公开了一个高级贝叶斯蒙特卡洛树搜索（MCTS）引擎，用于人工智能辅助分析和推理。

概述

此MCP服务器使Claude能够使用蒙特卡洛树搜索（MCTS）算法对主题、问题或文本输入进行深入的探索性分析。MCTS算法使用贝叶斯方法系统地探索不同的角度和解释，通过多次迭代产生有见地的分析。

特性

• 贝叶斯MCTS：在分析过程中使用概率方法来平衡勘探与开采
• 多次迭代分析：支持多次迭代思维，每次迭代进行多次模拟
• 状态持久性：在同一聊天中记住关键结果、不合适的方法和回合之间的先验
• 方法分类学：将产生的思想分为不同的哲学方法和家族
• 汤普森采样：可以使用Thompson采样或UCT进行节点选择
• 意外检测：确定令人惊讶或新颖的分析方向
• 意图分类：了解用户何时想要开始新的分析或继续之前的分析
• 多LLM支持：支持Ollama、OpenAI、Anthropic和Google Gemini模型。

快速启动安装

MCTS MCP服务器现在包括适用于Windows、macOS和Linux的跨平台设置脚本。

先决条件

• Python 3.10+ （必填）
• Internet连接 （用于下载依赖项）

自动设置

选项1：跨平台Python设置（推荐）

# Clone the repository
git clone https://github.com/angrysky56/mcts-mcp-server.git
cd mcts-mcp-server

# Run the setup script
python setup.py

选项2：特定于平台的脚本

Linux/macOS：

chmod +x setup.sh
./setup.sh

窗户：

setup_windows.bat

安装程序的作用

安装脚本会自动执行以下操作：

1. ✅ 检查Python版本兼容性（需要3.10+）
2. ✅ 安装UV包管理器（如果不存在）
3. ✅ 创建虚拟环境
4. ✅ 安装所有依赖项，包括谷歌genai
5. ✅ 创建 .env 模板文件
6. ✅ 生成Claude桌面配置
7. ✅ 创建状态目录
8. ✅ 验证安装

验证安装

设置后，验证一切正常：

python verify_installation.py

这会进行全面检查，并告诉您是否有任何需要修复的地方。

配置

1.API密钥设置

编辑 .env 安装过程中创建的文件：

# Add your API keys (remove quotes and add real keys)
OPENAI_API_KEY=sk-your-openai-key-here
ANTHROPIC_API_KEY=sk-ant-your-anthropic-key-here
GEMINI_API_KEY=your-gemini-api-key-here

# Set default provider and model (optional)
DEFAULT_LLM_PROVIDER=gemini
DEFAULT_MODEL_NAME=gemini-2.0-flash

获取API密钥：

• OpenAI: https://platform.openai.com/api-keys
• Anthropic: https://console.anthropic.com/
• 谷歌双子座: https://aistudio.google.com/app/apikey
• 奥拉马：不需要API密钥（本地模型）

2.克劳德桌面集成

设置创建 claude_desktop_config.json。将其内容添加到您的Claude Desktop配置中：

Linux/macOS：

# Config location
~/.config/claude/claude_desktop_config.json

窗户：

# Config location
%APPDATA%\Claude\claude_desktop_config.json

配置结构示例：

{
  "mcpServers": {
    "mcts-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcts-mcp-server/src",
        "run",
        "mcts-mcp-server"
      ],
      "env": {
        "UV_PROJECT_ENVIRONMENT": "/path/to/mcts-mcp-server"
      }
    }
  }
}

重要提示： 更新路径以匹配您的安装目录。

3.重新启动克劳德桌面

添加配置后，重新启动Claude Desktop以加载MCTS服务器。

用法

服务器以可复制粘贴的格式向您的LLM公开了许多工具，详细信息如下，用于您的系统提示。

当你让Claude对一个主题或问题进行深入分析时，它会自动利用这些工具，使用 MCTS算法和分析工具。

alt text

运作原理

MCTS MCP服务器使用本地推理方法，而不是尝试直接调用LLM。这与MCP协议兼容 是为人工智能助手（如克劳德）调用工具而设计的，而不是为工具本身调用人工智能模型而设计的。

当Claude要求服务器执行分析时，服务器：

1. 用问题初始化MCTS系统
2. 使用MCTS算法进行多次迭代探索
3. 为各种分析任务生成确定性响应
4. 返回搜索过程中找到的最佳分析

手动安装（高级）

如果您更喜欢手动设置或自动设置失败：

1.安装UV包管理器

Linux/macOS：

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows（PowerShell）：

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

2.设置项目

# Clone repository
git clone https://github.com/angrysky56/mcts-mcp-server.git
cd mcts-mcp-server

# Create virtual environment
uv venv .venv

# Activate virtual environment
# Linux/macOS:
source .venv/bin/activate
# Windows:
.venv\Scripts\activate

# Install dependencies
uv pip install .
uv pip install .[dev]  # Optional development dependencies

# Install Gemini package specifically (if not in pyproject.toml)
uv pip install google-genai>=1.20.0

3.创建配置文件

# Copy environment file
cp .env.example .env

# Edit .env file with your API keys
nano .env  # or use your preferred editor

# Create state directory
mkdir -p ~/.mcts_mcp_server

故障排除

常见问题

1.Python版本错误

Solution: Install Python 3.10+ from python.org

2.安装后未找到UV

# Add UV to PATH manually
export PATH="$HOME/.cargo/bin:$PATH"
# Or on Windows: Add %USERPROFILE%\.cargo\bin to PATH

3.谷歌Gemini导入错误

# Install Gemini package manually
uv pip install google-genai

4.权限被拒绝（Linux/macOS）

# Make scripts executable
chmod +x setup.sh setup_unix.sh

5.克劳德桌面未检测到服务器

• 验证配置文件位置和语法
• 检查配置中的路径是否绝对正确
• 完全重新启动克劳德桌面
• 检查Claude Desktop日志是否有错误

获取帮助

1. 运行验证: python verify_installation.py
2. 检查日志：查看Claude Desktop的开发工具
3. 测试组件：在存储库中运行单个测试
4. 审查文件：有关详细说明，请查看USAGE_GUIDE.md

API密钥管理

对于使用像OpenAI、Anthropic和Google Gemini这样的LLM提供商，您需要提供API密钥。此服务器从 .env 位于存储库根目录的文件。

1. 复制示例文件: cp .env.example .env
2. 编辑 .env：打开 .env 文件，并将占位符密钥替换为实际的API密钥：

   OPENAI_API_KEY="your_openai_api_key_here"
   ANTHROPIC_API_KEY="your_anthropic_api_key_here"
   GEMINI_API_KEY="your_google_gemini_api_key_here"

1. 设置默认值（可选）：您还可以在 .env 文件：

   # Default LLM Provider to use (e.g., "ollama", "openai", "anthropic", "gemini")
   DEFAULT_LLM_PROVIDER="ollama"
   # Default Model Name for the selected provider
   DEFAULT_MODEL_NAME="cogito:latest"

如果未设置这些，系统将默认为“ollama”，并尝试使用“cogito:latest”等模型或其他特定于提供商的默认值。

这 .env 文件包含在 .gitignore，因此您的实际密钥将不会提交到存储库。

建议的系统提示和更新工具

______________________________________________________________________

# MCTS server and usage instructions:

# List available Ollama models (if using Ollama)
list_ollama_models()

# Set the active LLM provider and model
# provider_name can be "ollama", "openai", "anthropic", "gemini"
# model_name is specific to the provider (e.g., "cogito:latest" for ollama, "gpt-4" for openai)
set_active_llm(provider_name="openai", model_name="gpt-3.5-turbo")
# Or, to use defaults from .env or provider-specific defaults:
# set_active_llm(provider_name="openai")

# Initialize analysis (can also specify provider and model here to override active settings for this run)
initialize_mcts(question="Your question here", chat_id="unique_id", provider_name="openai", model_name="gpt-4")
# Or using the globally set active LLM:
# initialize_mcts(question="Your question here", chat_id="unique_id")

run_mcts(iterations=1, simulations_per_iteration=5)

After run_mcts is called it can take quite a long time ie minutes to hours
- so you may discuss any ideas or questions or await user confirmation of the process finishing,
- then proceed to synthesis and analysis tools on resumption of chat.

## MCTS-MCP Tools Overview

### Core MCTS Tools:
- `initialize_mcts`: Start a new MCTS analysis with a specific question. Can optionally specify `provider_name` and `model_name` to override defaults for this run.
- `run_mcts`: Run the MCTS algorithm for a set number of iterations/simulations.
- `generate_synthesis`: Generate a final summary of the MCTS results.
- `get_config`: View current MCTS configuration parameters, including active LLM provider and model.
- `update_config`: Update MCTS configuration parameters (excluding provider/model, use `set_active_llm` for that).
- `get_mcts_status`: Check the current status of the MCTS system.
- `set_active_llm(provider_name: str, model_name: Optional[str])`: Select which LLM provider and model to use for MCTS.
- `list_ollama_models()`: Show all available local Ollama models (if using Ollama provider).

Default configuration prioritizes speed and exploration, but you can customize parameters like exploration_weight, beta_prior_alpha/beta, surprise_threshold.

## Configuration

You can customize the MCTS parameters in the config dictionary or through Claude's `update_config` tool. Key parameters include:

- `max_iterations`: Number of MCTS iterations to run
- `simulations_per_iteration`: Number of simulations per iteration
- `exploration_weight`: Controls exploration vs. exploitation balance (in UCT)
- `early_stopping`: Whether to stop early if a high-quality solution is found
- `use_bayesian_evaluation`: Whether to use Bayesian evaluation for node scores
- `use_thompson_sampling`: Whether to use Thompson sampling for selection

Articulating Specific Pathways:
Delving into the best_path nodes (using mcts_instance.get_best_path_nodes() if you have the instance) and examining the sequence of thought and content
at each step can provide a fascinating micro-narrative of how the core insight evolved.

Visualizing the tree (even a simplified version based on export_tree_summary) could also be illuminating and I will try to set up this feature.

Modifying Parameters: This is a great way to test the robustness of the finding or explore different "cognitive biases" of the system.

Increasing Exploration Weight: Might lead to more diverse, less obviously connected ideas.

Decreasing Exploration Weight: Might lead to deeper refinement of the initial dominant pathways.

Changing Priors (if Bayesian): You could bias the system towards certain approaches (e.g., increase alpha for 'pragmatic') to see how it influences the
outcome.

More Iterations/Simulations: Would allow for potentially deeper convergence or exploration of more niche pathways.

### Results Collection:
- Automatically stores results in `/home/ty/Repositories/ai_workspace/mcts-mcp-server/results` (path might be system-dependent or configurable)
- Organizes by provider, model name, and run ID
- Stores metrics, progress info, and final outputs

# MCTS Analysis Tools

This extension adds powerful analysis tools to the MCTS-MCP Server, making it easy to extract insights and understand results from your MCTS runs.

The MCTS Analysis Tools provide a suite of integrated functions to:

1. List and browse MCTS runs
2. Extract key concepts, arguments, and conclusions
3. Generate comprehensive reports
4. Compare results across different runs
5. Suggest improvements for better performance

## Available Run Analysis Tools

### Browsing and Basic Information

- `list_mcts_runs(count=10, model=None)`: List recent MCTS runs with key metadata
- `get_mcts_run_details(run_id)`: Get detailed information about a specific run
- `get_mcts_solution(run_id)`: Get the best solution from a run

### Analysis and Insights

- `analyze_mcts_run(run_id)`: Perform a comprehensive analysis of a run
- `get_mcts_insights(run_id, max_insights=5)`: Extract key insights from a run
- `extract_mcts_conclusions(run_id)`: Extract conclusions from a run
- `suggest_mcts_improvements(run_id)`: Get suggestions for improvement

### Reporting and Comparison

- `get_mcts_report(run_id, format='markdown')`: Generate a comprehensive report (formats: 'markdown', 'text', 'html')
- `get_best_mcts_runs(count=5, min_score=7.0)`: Get the best runs based on score
- `compare_mcts_runs(run_ids)`: Compare multiple runs to identify similarities and differences

## Usage Examples

# To list your recent MCTS runs:

list_mcts_runs()

# To get details about a specific run:

get_mcts_run_details('ollama_cogito:latest_1745979984') # Example run_id format

### Extracting Insights

# To get key insights from a run:

get_mcts_insights(run_id='ollama_cogito:latest_1745979984')

### Generating Reports

# To generate a comprehensive markdown report:

get_mcts_report(run_id='ollama_cogito:latest_1745979984', format='markdown')

### Improving Results

# To get suggestions for improving a run:

suggest_mcts_improvements(run_id='ollama_cogito:latest_1745979984')

### Comparing Runs

To compare multiple runs:

compare_mcts_runs(['ollama_cogito:latest_1745979984', 'openai_gpt-3.5-turbo_1745979584']) # Example run_ids

## Understanding the Results

The analysis tools extract several key elements from MCTS runs:

1. **Key Concepts**: The core ideas and frameworks in the analysis
2. **Arguments For/Against**: The primary arguments on both sides of a question
3. **Conclusions**: The synthesized conclusions or insights from the analysis
4. **Tags**: Automatically generated topic tags from the content

## Troubleshooting

If you encounter any issues with the analysis tools:

1. Check that your MCTS run completed successfully (status: "completed")
2. Verify that the run ID you're using exists and is correct
3. Try listing all runs to see what's available: `list_mcts_runs()`
4. Make sure the `.best_solution.txt` file exists in the run's directory

## Advanced Example Usage

### Customizing Reports

You can generate reports in different formats:

# Generate a markdown report

report = get_mcts_report(run_id='ollama_cogito:latest_1745979984', format='markdown')

# Generate a text report

report = get_mcts_report(run_id='ollama_cogito:latest_1745979984', format='text')

# Generate an HTML report

report = get_mcts_report(run_id='ollama_cogito:latest_1745979984', format='html')

### Finding the Best Runs

To find your best-performing runs:

best_runs = get_best_mcts_runs(count=3, min_score=8.0)

This returns the top 3 runs with a score of at least 8.0.

## Simple Usage Instructions

1. **Setting the LLM Provider and Model**:
   # For Ollama:
   list_ollama_models()  # See available Ollama models
   set_active_llm(provider_name="ollama", model_name="cogito:latest")

   # For OpenAI:
   set_active_llm(provider_name="openai", model_name="gpt-4")

   # For Anthropic:
   set_active_llm(provider_name="anthropic", model_name="claude-3-opus-20240229")

   # For Gemini:
   set_active_llm(provider_name="gemini", model_name="gemini-1.5-pro-latest")

2. **Starting a New Analysis**:
   # Uses the LLM set by set_active_llm, or defaults from .env
   initialize_mcts(question="Your question here", chat_id="unique_identifier")
   # Alternatively, specify provider/model for this specific analysis:
   # initialize_mcts(question="Your question here", chat_id="unique_identifier", provider_name="openai", model_name="gpt-4-turbo")

3. **Running the Analysis**:

   run_mcts(iterations=3, simulations_per_iteration=10)

4. **Comparing Performance (Ollama specific example)**:

   run_model_comparison(question="Your question", iterations=2)

5. **Getting Results**:

   generate_synthesis()  # Final summary of results
   get_mcts_status()     # Current status and metrics

______________________________________________________________________

示例提示

• “分析人工智能对人类创造力的影响”
• “继续探索这一主题的伦理维度”
• “你在上次运行中发现的最佳分析是什么？”
• “这个MCTS流程是如何工作的？”
• “显示当前MCTS配置”

alt text

对于开发者

开发设置

# Activate virtual environment
source .venv/bin/activate

# Install development dependencies
uv pip install .[dev]

# Run the server directly (for testing)
uv run server.py

# OR use the MCP CLI tools
uv run -m mcp dev server.py

测试服务器

要测试服务器是否正常工作，请执行以下操作：

# Activate the virtual environment
source .venv/bin/activate

# Run the verification script
python verify_installation.py

# Run the test script
python test_server.py

这将测试LLM适配器，以确保其正常工作。

项目结构

mcts-mcp-server/
├── src/mcts_mcp_server/          # Main package
│   ├── adapters/                 # LLM adapters
│   ├── analysis_tools/           # Analysis and reporting tools
│   ├── mcts_core.py             # Core MCTS algorithm
│   ├── tools.py                 # MCP tools
│   └── server.py                # MCP server
├── setup.py                     # Cross-platform setup script
├── setup.sh                     # Unix setup script
├── setup_windows.bat            # Windows setup script
├── verify_installation.py       # Installation verification
├── pyproject.toml               # Project configuration
├── .env.example                 # Environment template
└── README.md                    # This file

贡献

欢迎为改进MCTS MCP服务器做出贡献。一些潜在的改进领域：

• 改进本地推理适配器以进行更复杂的分析
• 添加更复杂的思维模式和评估策略
• 增强树可视化和结果报告
• 优化MCTS算法参数

开发工作流程

1. 分叉存储库
2. 运行安装程序: python setup.py
3. 验证安装: python verify_installation.py
4. 进行更改
5. 测试更改: python test_server.py
6. 提交拉取请求

许可证： 麻省理工学院