Skip to main content
Glama
taylorleese

mcp-toolz

MCP Toolz

mcp-name: io.github.taylorleese/mcp-toolz

CI GitHub issues GitHub last commit codecov PyPI version Python MCP License: MIT

pre-commit OpenSSF Best Practices OpenSSF Scorecard Dependabot

为 Claude Code 提供的 MCP 服务器,提供多 LLM 反馈工具和剪贴板图像捕获功能。

功能特性

  • 多 LLM 反馈:从 ChatGPT (OpenAI)、Claude (Anthropic)、Gemini (Google) 和 DeepSeek 获取第二意见

  • 剪贴板图像捕获:将 macOS 剪贴板中的图像直接粘贴到 Claude Code 中进行分析

  • MCP 集成:通过模型上下文协议 (Model Context Protocol) 与 Claude Code 协同工作

Related MCP server: Todoist MCP

快速入门

安装

从 PyPI 安装(推荐)

pip install mcp-toolz

从源码安装(开发)

# Clone the repository
git clone https://github.com/taylorleese/mcp-toolz.git
cd mcp-toolz

# Create and activate virtual environment
python3 -m venv venv
source venv/bin/activate  # macOS/Linux
# or: venv\Scripts\activate  # Windows

# Install in editable mode with dev dependencies
pip install -e ".[dev]"

配置

# Set your API keys as environment variables (at least one required for AI feedback tools)
export OPENAI_API_KEY=sk-...           # For ChatGPT
export ANTHROPIC_API_KEY=sk-ant-...    # For Claude
export GOOGLE_API_KEY=...              # For Gemini
export DEEPSEEK_API_KEY=sk-...         # For DeepSeek

# Or create a .env file (if installing from source)
cp .env.example .env
# Edit .env and add your API keys

MCP 服务器设置

添加到您的 Claude Code MCP 设置中:

如果通过 pip 安装:

{
  "mcpServers": {
    "mcp-toolz": {
      "command": "python",
      "args": ["-m", "mcp_server"],
      "env": {
        "OPENAI_API_KEY": "sk-...",
        "ANTHROPIC_API_KEY": "sk-ant-...",
        "GOOGLE_API_KEY": "...",
        "DEEPSEEK_API_KEY": "sk-..."
      }
    }
  }
}

如果从源码安装:

{
  "mcpServers": {
    "mcp-toolz": {
      "command": "python",
      "args": ["-m", "mcp_server"],
      "cwd": "/absolute/path/to/mcp-toolz",
      "env": {
        "PYTHONPATH": "/absolute/path/to/mcp-toolz/src"
      }
    }
  }
}

重启 Claude Code 以加载 MCP 服务器。

MCP 服务器工具

AI 反馈工具

针对代码、架构决策和实施计划从多个 LLM 获取第二意见:

  • ask_chatgpt - 获取 ChatGPT 的分析(支持自定义问题)

  • ask_claude - 获取 Claude 的分析(支持自定义问题)

  • ask_gemini - 获取 Gemini 的分析(支持自定义问题)

  • ask_deepseek - 获取 DeepSeek 的分析(支持自定义问题)

剪贴板图像工具

  • paste_image - 从 macOS 剪贴板捕获图像以进行分析(支持可选问题)

Claude Code 技能

/resolve-github-alerts

自动分类并解决 GitHub 安全警报(Dependabot、代码扫描、密钥扫描)。在 Claude Code 中运行它以:

  • 修复失败的 Dependabot PR(lint/测试问题)

  • 升级易受攻击的依赖项并重新编译需求

  • 修复代码扫描和密钥扫描警报

  • 提交包含所有修复的单个 PR 以供人工审核

/resolve-github-alerts

使用示例

获取多个 AI 视角

I'm deciding between Redis and Memcached for caching user sessions.
Ask ChatGPT for their analysis.

后续操作:

  • “Ask Claude the same question for comparison”

  • “Ask Gemini for another perspective”

  • “What does DeepSeek think about this?”

分析剪贴板图像

将图像复制到剪贴板(截图、图表、错误消息等),然后:

Analyze my clipboard image

或者带上具体问题:

What's wrong with the UI layout in my clipboard image?

多视角调试

I'm getting "TypeError: Cannot read property 'map' of undefined" in my React component.
The error occurs in UserList.jsx when rendering the users array.
Ask ChatGPT and Claude for debugging suggestions.

环境变量

# Required (at least one for AI feedback tools)
OPENAI_API_KEY=sk-...                              # Your OpenAI API key
ANTHROPIC_API_KEY=sk-ant-...                       # Your Anthropic API key
GOOGLE_API_KEY=...                                 # Your Google API key (for Gemini)
DEEPSEEK_API_KEY=sk-...                            # Your DeepSeek API key

# Optional
MCP_TOOLZ_MODEL=gpt-5                                         # OpenAI model (default: gpt-5)
MCP_TOOLZ_CLAUDE_MODEL=claude-sonnet-4-5-20250929             # Claude model
MCP_TOOLZ_GEMINI_MODEL=gemini-2.0-flash-thinking-exp-01-21   # Gemini model
MCP_TOOLZ_DEEPSEEK_MODEL=deepseek-chat                        # DeepSeek model

故障排除

“Error 401: Invalid API key”

  • 验证 API 密钥是否已在 .env 或环境变量中设置

  • 检查您的 API 提供商账户是否已启用计费

“No module named context_manager”

  • 在直接运行 Python 之前使用 PYTHONPATH=src

  • 或者通过 pip 安装:pip install mcp-toolz

“No image found in clipboard”

  • 请先复制一张图像(截图、右键点击 > 复制图像等)

  • paste_image 工具需要 macOS(使用 AppleScript 读取剪贴板)

项目结构

mcp-toolz/
├── src/
│   ├── mcp_server/              # MCP server for Claude Code
│   │   └── server.py            # MCP tools and handlers
│   └── context_manager/         # Client implementations
│       ├── openai_client.py     # ChatGPT API client
│       ├── anthropic_client.py  # Claude API client
│       ├── gemini_client.py     # Gemini API client
│       ├── deepseek_client.py   # DeepSeek API client
│       └── clipboard.py         # macOS clipboard image capture
├── tests/                       # pytest tests
├── requirements.in
└── requirements.txt

开发

贡献者设置

# Clone and install
git clone https://github.com/taylorleese/mcp-toolz.git
cd mcp-toolz
python3 -m venv venv
source venv/bin/activate
pip install -r requirements-dev.txt

# Install pre-commit hooks (IMPORTANT!)
pre-commit install

# Copy and configure .env
cp .env.example .env
# Edit .env with your API keys

运行测试

source venv/bin/activate
pytest

代码质量

pre-commit Code style: black Ruff mypy isort security: bandit

# Run all checks (runs automatically on commit after pre-commit install)
pre-commit run --all-files

# Individual tools
black .
ruff check .
mypy src/

许可证

MIT

Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - A tier

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/taylorleese/mcp-toolz'

If you have feedback or need assistance with the MCP directory API, please join our Discord server