MCP Toolbox
A comprehensive toolkit that enhances LLM capabilities through the Model Context Protocol, allowing LLMs to interact with external services including command-line operations, file management, Figma integration, and audio processing.
What is MCP Toolbox?
MCP Toolbox is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to comprehensive toolkit that enhances llm capabilities through the model context protocol, allowing llms to interact with external services including command-line operations, file management, figma inte...
A comprehensive toolkit that enhances LLM capabilities through the Model Context Protocol, allowing LLMs to interact with external services including command-line operations, file management, Figma integration, and audio processing.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A comprehensive toolkit that enhances LLM capabilities throu
Use Cases
Maintainer
Works with
Installation
NPM
npx -y mcp-toolboxManual Installation
npx -y mcp-toolboxConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Toolbox
MCP Toolbox (by ai-zerolab) is a comprehensive Python-based MCP server that bundles multiple capability groups into a single installable package: shell command execution, file read/write and directory management, Figma design file access, web search via Tavily or DuckDuckGo, URL-to-Markdown conversion, audio transcription, semantic memory with thought logging, podcast downloads, and Flux AI image generation. Developers and power users reach for it when they want a single MCP server that covers the most common LLM tool needs without configuring a dozen separate servers, with each capability group activatable via optional dependency extras.
Prerequisites
- Python 3.10 or later with uv or pip installed
- FIGMA_API_KEY if using Figma integration (from Figma account settings)
- TAVILY_API_KEY if using Tavily web search (from tavily.com)
- BFL_API_KEY if using Flux image generation (from api.bfl.ml)
- An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code
Install the package with all extras
Use uvx to run without a permanent install, or pip to install globally. The [all] extra enables every capability group.
# Run directly with uvx (recommended, no install needed)
uvx "mcp-toolbox[all]@latest" stdio
# Or install globally with pip
pip install "mcp-toolbox[all]"Set API keys as environment variables
Export the keys for the capability groups you plan to use. Only keys for features you want are required.
export FIGMA_API_KEY=your_figma_key
export TAVILY_API_KEY=your_tavily_key
export BFL_API_KEY=your_bfl_keyConfigure your MCP client
Add the toolbox server to your MCP client's config file. The uvx approach is the most portable and always runs the latest version.
{
"mcpServers": {
"zerolab-toolbox": {
"command": "uvx",
"args": ["--prerelease=allow", "mcp-toolbox[all]@latest", "stdio"],
"env": {
"FIGMA_API_KEY": "your_figma_key",
"TAVILY_API_KEY": "your_tavily_key",
"BFL_API_KEY": "your_bfl_key"
}
}
}
}Restart your MCP client
After saving the config, fully quit and reopen your MCP client so it detects the new server.
Verify the server is connected
Ask your AI client to list available tools or run a simple file listing to confirm the server is active.
MCP Toolbox Examples
Client configuration
Full JSON config block for Claude Desktop using uvx with all optional extras and API keys.
{
"mcpServers": {
"zerolab-toolbox": {
"command": "uvx",
"args": ["--prerelease=allow", "mcp-toolbox[all]@latest", "stdio"],
"env": {
"FIGMA_API_KEY": "your_figma_api_key",
"TAVILY_API_KEY": "your_tavily_api_key",
"BFL_API_KEY": "your_bfl_api_key"
}
}
}
}Prompts to try
Example prompts covering each major capability group in the toolbox.
- "What files are in the current directory?"
- "Read the file at /home/user/notes.txt and summarize it"
- "Search the web for 'latest developments in AI agents 2025'"
- "Fetch this URL and convert it to Markdown: https://example.com"
- "Get information about Figma file with key abc123def456"
- "Transcribe the audio from /home/user/meeting.mp3 between 0 and 120 seconds"
- "Remember this: my preferred code style is 2-space indentation"
- "Generate an image of a futuristic city skyline at sunset"Troubleshooting MCP Toolbox
uvx command not found
Install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux) or see astral.sh for Windows. Then retry 'uvx mcp-toolbox[all]@latest stdio'.
Figma tools return 'unauthorized' errors
Check that FIGMA_API_KEY is set correctly. Generate a personal access token in Figma under Account Settings > Security > Personal access tokens.
Web search tools return no results or fail
For Tavily, confirm TAVILY_API_KEY is valid and your account has remaining credits. As an alternative, DuckDuckGo search requires DUCKDUCKGO_API_KEY if using the paid API, or may work without a key in free mode depending on the installed version.
Frequently Asked Questions about MCP Toolbox
What is MCP Toolbox?
MCP Toolbox is a Model Context Protocol (MCP) server that comprehensive toolkit that enhances llm capabilities through the model context protocol, allowing llms to interact with external services including command-line operations, file management, figma integration, and audio processing. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Toolbox?
Install via npm with the command: npx -y mcp-toolbox. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with MCP Toolbox?
MCP Toolbox works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Toolbox free to use?
Yes, MCP Toolbox is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
MCP Toolbox Alternatives — Similar Developer Tools Servers
Looking for alternatives to MCP Toolbox? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Toolbox in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Toolbox?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.