MCP server
by ai-zerolab
Toolbox integrates APIs and services for LLM command execution, UI/UX design, and risk management API integration platfo
Provides command-line execution, Figma file access, and file operations through MCP protocol. Extends LLM capabilities to interact with external services and APIs.
Toolbox is a community-built MCP server published by ai-zerolab that provides AI assistants with tools and capabilities via the Model Context Protocol. Toolbox integrates APIs and services for LLM command execution, UI/UX design, and risk management API integration platfo It is categorized under developer tools.
You can install Toolbox in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
Apache-2.0
Toolbox is released under the Apache-2.0 license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
According to our notes, Toolbox benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Toolbox reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
According to our notes, Toolbox benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Toolbox has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
We wired Toolbox into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Toolbox is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Strong directory entry: Toolbox surfaces stars and publisher context so we could sanity-check maintenance before adopting.
We wired Toolbox into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Toolbox is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Toolbox is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
showing 1-10 of 31
A comprehensive toolkit for enhancing LLM capabilities through the Model Context Protocol (MCP). This package provides a collection of tools that allow LLMs to interact with external services and APIs, extending their functionality beyond text generation.
*nix is our main target, but Windows should work too.
We recommend using uv to manage your environment.
# 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
Then you can use uvx "mcp-toolbox@latest" stdio as commands for running the MCP server for latest version. Audio and memory tools are not included in the default installation., you can include them by installing the all extra:
[audio] for audio tools, [memory] for memory tools, [all] for all tools
uvx "mcp-toolbox[all]@latest" stdio
To install Toolbox for LLM Enhancement for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @ai-zerolab/mcp-toolbox --client claude
pip install "mcp-toolbox[all]"
And you can use mcp-toolbox stdio as commands for running the MCP server.
The following environment variables can be configured:
FIGMA_API_KEY: API key for Figma integrationTAVILY_API_KEY: API key for Tavily integrationDUCKDUCKGO_API_KEY: API key for DuckDuckGo integrationBFL_API_KEY: API key for Flux image generation APIMemory tools store data in the following locations:
~/Documents/zerolab/mcp-toolbox/memory (syncs across devices via iCloud)~/.zerolab/mcp-toolbox/memoryTo use mcp-toolbox with Claude Desktop/Cline/Cursor/..., add the following 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"
}
}
}
}
For full features:
{
"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"
}
}
}
}
You can generate a debug configuration template using:
uv run generate_config_template.py
| Tool | Description |
|---|---|
execute_command | Execute a command line instruction |
| Tool | Description |
|---|---|
read_file_content | Read content from a file |
write_file_content | Write content to a file |
replace_in_file | Replace content in a file using regular expressions |
list_directory | List directory contents with detailed information |
| Tool | Description |
|---|---|
figma_get_file | Get a Figma file by key |
figma_get_file_nodes | Get specific nodes from a Figma file |
figma_get_image | Get images for nodes in a Figma file |
figma_get_image_fills | Get URLs for images used in a Figma file |
figma_get_comments | Get comments on a Figma file |
figma_post_comment | Post a comment on a Figma file |
figma_delete_comment | Delete a comment from a Figma file |
figma_get_team_projects | Get projects for a team |
figma_get_project_files | Get files for a project |
figma_get_team_components | Get components for a team |
figma_get_file_components | Get components from a file |
figma_get_component | Get a component by key |
figma_get_team_component_sets | Get component sets for a team |
figma_get_team_styles | Get styles for a team |
figma_get_file_styles | Get styles from a file |
figma_get_style | Get a style by key |
| Tool | Description |
|---|---|
xiaoyuzhoufm_download | Download a podcast episode from XiaoyuZhouFM with optional automatic m4a to mp3 conversion |
| Tool | Description |
|---|---|
get_audio_length | Get the length of an audio file in seconds |
get_audio_text | Get transcribed text from a specific time range in an audio file |
| Tool | Description |
|---|---|
think | Use the tool to think about something and append the thought to the log |
get_session_id | Get the current session ID |
remember | Store a memory (brief and detail) in the memory database |
recall | Query memories from the database with semantic search |
forget | Clear all memories in the memory database |
| Tool | Description |
|---|---|
convert_file_to_markdown | Convert any file to Markdown using MarkItDown |
convert_url_to_markdown | Convert a URL to Markdown using MarkItDown |
| Tool | Description |
|---|---|
get_html | Get HTML content from a URL |
save_html | Save HTML from a URL to a file |
search_with_tavily | Search the web using Tavily (requires API key) |
search_with_duckduckgo | Search the web using DuckDuckGo (requires API key) |
| Tool | Description |
|---|---|
flux_generate_image | Generate an image using the Flux API and save it to a file |
# Run with stdio transport (default)
mcp-toolbox stdio
# Run with SSE transport
mcp-toolbox sse --host localhost --port 9871
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.