mcp-toolz 0.5.0

Get feedback from ChatGPT, Claude, Gemini, and DeepSeek via MCP tools

MCP Toolz

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

MCP server for Claude Code that provides multi-LLM feedback tools and clipboard image capture.

Features

• Multi-LLM Feedback: Get second opinions from ChatGPT (OpenAI), Claude (Anthropic), Gemini (Google), and DeepSeek
• Clipboard Image Capture: Paste images from your macOS clipboard directly into Claude Code for analysis
• MCP Integration: Works with Claude Code via the Model Context Protocol

Quick Start

Installation

From PyPI (Recommended)

pip install mcp-toolz

From Source (Development)

# 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]"

Configuration

# 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 Server Setup

Add to your Claude Code MCP settings:

If installed via pip:

{
  "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-..."
      }
    }
  }
}

If installed from source:

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

Restart Claude Code to load the MCP server.

MCP Server Tools

AI Feedback Tools

Get second opinions from multiple LLMs on code, architecture decisions, and implementation plans:

• ask_chatgpt - Get ChatGPT's analysis (supports custom questions)
• ask_claude - Get Claude's analysis (supports custom questions)
• ask_gemini - Get Gemini's analysis (supports custom questions)
• ask_deepseek - Get DeepSeek's analysis (supports custom questions)

Clipboard Image Tool

• paste_image - Capture an image from the macOS clipboard for analysis (supports optional question)

Usage Examples

Get Multiple AI Perspectives

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

Follow up with:

• "Ask Claude the same question for comparison"
• "Ask Gemini for another perspective"
• "What does DeepSeek think about this?"

Analyze a Clipboard Image

Copy an image to your clipboard (screenshot, diagram, error message, etc.), then:

Analyze my clipboard image

Or with a specific question:

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

Debug with Multiple Perspectives

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.

Environment Variables

# 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

Troubleshooting

"Error 401: Invalid API key"

• Verify API keys are set in .env or environment variables
• Check billing is enabled on your API provider account

"No module named context_manager"

• Use PYTHONPATH=src before running Python directly
• Or install via pip: pip install mcp-toolz

"No image found in clipboard"

• Copy an image first (screenshot, right-click > Copy Image, etc.)
• The paste_image tool requires macOS (uses AppleScript to read the clipboard)

Project Structure

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

Development

Setup for Contributors

# 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

Running Tests

source venv/bin/activate
pytest

Code Quality

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

# Individual tools
black .
ruff check .
mypy src/

License

MIT