MCP Toolbox MCP Server

A comprehensive toolkit for enhancing LLM capabilities through the Model Context Protocol (MCP). This package provides a collection of tools that

Local serverstdioPython

What is the MCP Toolbox MCP server?

MCP Toolbox MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. 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.

What you get

  • Command Line Execution — Execute any command line instruction through LLM
  • Figma Integration — Access Figma files, components, styles, and more
  • Extensible Architecture — Easily add new API integrations
  • MCP Protocol Support — Compatible with Claude Desktop and other MCP-enabled LLMs
  • Comprehensive Testing — Well-tested codebase with high test coverage

What the assistant can call

Once MCP Toolbox is connected, these are the calls the assistant has available:

  • execute_command — Execute a command line instruction
  • 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
  • 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

Configuration and credentials

You will need 4 environment variables: FIGMA_API_KEY, TAVILY_API_KEY, DUCKDUCKGO_API_KEY, BFL_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Toolbox's toolset — execute_command, read_file_content, write_file_content and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ai-zerolab; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP Toolbox.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp toolbox mcp server does with a few real requests.

Available tools

ToolWhat it does
execute_commandExecute a command line instruction
read_file_contentRead content from a file
write_file_contentWrite content to a file
replace_in_fileReplace content in a file using regular expressions
list_directoryList directory contents with detailed information
figma_get_fileGet a Figma file by key
figma_get_file_nodesGet specific nodes from a Figma file
figma_get_imageGet images for nodes in a Figma file
figma_get_image_fillsGet URLs for images used in a Figma file
figma_get_commentsGet comments on a Figma file
figma_post_commentPost a comment on a Figma file
figma_delete_commentDelete a comment from a Figma file
figma_get_team_projectsGet projects for a team
figma_get_project_filesGet files for a project

How to install the MCP Toolbox MCP server

{
  "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"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
FIGMA_API_KEYCredential the server authenticates with.Yes
TAVILY_API_KEYCredential the server authenticates with.Yes
DUCKDUCKGO_API_KEYCredential the server authenticates with.Yes
BFL_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use MCP Toolbox to execute command.
  • Use MCP Toolbox to read file content.
  • Use MCP Toolbox to write file content.

Frequently asked questions

It connects MCP Toolbox to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (execute_command, read_file_content, write_file_content, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Toolbox directly.