Toolbox MCP server

MCP Toolbox is a comprehensive toolkit that extends the capabilities of Large Language Models (LLMs) through the Model Context Protocol (MCP). It enables LLMs to interact with external services and APIs including command line execution, Figma integration, file operations, web tools, and more.

Installation Options

Using uv (Recommended)

# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh  # For macOS/Linux
# or
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"  # For Windows

# Run MCP server (latest version)
uvx "mcp-toolbox@latest" stdio

# For full features including audio and memory tools
uvx "mcp-toolbox[all]@latest" stdio

Installing via Smithery

npx -y @smithery/cli install @ai-zerolab/mcp-toolbox --client claude

Using pip

pip install "mcp-toolbox[all]"
mcp-toolbox stdio  # Run the MCP server

Configuration

Environment Variables

Configure these environment variables for full functionality:

• FIGMA_API_KEY: For Figma integration
• TAVILY_API_KEY: For Tavily search
• DUCKDUCKGO_API_KEY: For DuckDuckGo search
• BFL_API_KEY: For Flux image generation

Memory Storage Locations

• macOS: ~/Documents/zerolab/mcp-toolbox/memory (syncs via iCloud)
• Other platforms: ~/.zerolab/mcp-toolbox/memory

Claude Desktop Configuration

Add this to your Claude configuration file:

{
  "mcpServers": {
    "zerolab-toolbox": {
      "command": "uvx",
      "args": ["--prerelease=allow", "mcp-toolbox@latest", "stdio"],
      "env": {
        "FIGMA_API_KEY": "your-figma-api-key",
        "TAVILY_API_KEY": "your-tavily-api-key",
        "DUCKDUCKGO_API_KEY": "your-duckduckgo-api-key",
        "BFL_API_KEY": "your-bfl-api-key"
      }
    }
  }
}

For all features including audio and memory tools:

{
  "mcpServers": {
    "zerolab-toolbox": {
      "command": "uvx",
      "args": [
        "--prerelease=allow",
        "--python=3.12",
        "mcp-toolbox[all]@latest",
        "stdio"
      ],
      "env": {
        "FIGMA_API_KEY": "your-figma-api-key",
        "TAVILY_API_KEY": "your-tavily-api-key",
        "DUCKDUCKGO_API_KEY": "your-duckduckgo-api-key",
        "BFL_API_KEY": "your-bfl-api-key"
      }
    }
  }
}

Generate a debug configuration template with:

uv run generate_config_template.py

Available Tools

Command Line Tools

• execute_command: Execute command line instructions

File Operations Tools

• read_file_content: Read content from files
• write_file_content: Write content to files
• replace_in_file: Replace content using regex
• list_directory: List directory contents with details

Figma Tools

• Multiple tools for working with Figma files, components, styles, and comments

Web Tools

• get_html: Get HTML from a URL
• save_html: Save HTML from a URL to a file
• search_with_tavily: Search using Tavily
• search_with_duckduckgo: Search using DuckDuckGo

Audio Tools

• get_audio_length: Get audio file duration
• get_audio_text: Transcribe audio from time ranges

Memory Tools

• think: Log thoughts to memory
• get_session_id: Get current session ID
• remember: Store memories
• recall: Query memories with semantic search
• forget: Clear memory database

Markitdown Tools

• convert_file_to_markdown: Convert files to Markdown
• convert_url_to_markdown: Convert URLs to Markdown

Flux Image Generation Tools

• flux_generate_image: Generate and save images

XiaoyuZhouFM Tools

• xiaoyuzhoufm_download: Download podcast episodes

Usage Examples

Running the MCP Server

# With stdio transport (default)
mcp-toolbox stdio

# With SSE transport
mcp-toolbox sse --host localhost --port 9871

Examples With Claude Desktop

After configuring Claude Desktop:

• Figma interactions:

  • "Get information about this Figma file: 12345abcde"
  • "Show me the components in this Figma file: 12345abcde"

• Command line operations:

  • "What files are in the current directory?"
  • "What's the current system time?"

• Podcast downloads:

  • "Download this podcast episode: https://www.xiaoyuzhoufm.com/episode/67c3d80fb0167b8db9e3ec0f"

• Audio processing:

  • "What's the length of audio.m4a?"
  • "Transcribe the audio from 60 to 90 seconds in audio.m4a"

• File conversion:

  • "Convert document.docx to Markdown"
  • "Convert https://example.com to Markdown"

• Web operations:

  • "Get the HTML from https://example.com"
  • "Search for 'artificial intelligence news'"

• Image generation:

  • "Generate an image of a beautiful sunset over mountains"

• Memory operations:

  • "Remember this: The capital of France is Paris"
  • "Recall any information about France"
  • "What's my current session ID?"

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "zerolab-toolbox" '{"command":"uvx","args":["--prerelease=allow","mcp-toolbox@latest","stdio"],"env":{"FIGMA_API_KEY":"your-figma-api-key","TAVILY_API_KEY":"your-tavily-api-key","DUCKDUCKGO_API_KEY":"your-duckduckgo-api-key","BFL_API_KEY":"your-bfl-api-key"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "zerolab-toolbox": {
            "command": "uvx",
            "args": [
                "--prerelease=allow",
                "mcp-toolbox@latest",
                "stdio"
            ],
            "env": {
                "FIGMA_API_KEY": "your-figma-api-key",
                "TAVILY_API_KEY": "your-tavily-api-key",
                "DUCKDUCKGO_API_KEY": "your-duckduckgo-api-key",
                "BFL_API_KEY": "your-bfl-api-key"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "zerolab-toolbox": {
            "command": "uvx",
            "args": [
                "--prerelease=allow",
                "mcp-toolbox@latest",
                "stdio"
            ],
            "env": {
                "FIGMA_API_KEY": "your-figma-api-key",
                "TAVILY_API_KEY": "your-tavily-api-key",
                "DUCKDUCKGO_API_KEY": "your-duckduckgo-api-key",
                "BFL_API_KEY": "your-bfl-api-key"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect