MCP.so
Sign In

Penpot Mcp

@montevive

About Penpot Mcp

Penpot MCP is a revolutionary Model Context Protocol (MCP) server that bridges the gap between AI language models and Penpot, the open-source design and prototyping platform. This integration enables AI assistants like Claude (in both Claude Desktop and Cursor IDE) to understand,

Basic information

Category

Developer Tools

Transports

stdio

Publisher

montevive

Submitted by

JM Robles

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "penpot": {
      "command": "uvx",
      "args": [
        "penpot-mcp"
      ],
      "env": {
        "PENPOT_API_URL": "https://design.penpot.app/api",
        "PENPOT_USERNAME": "your_penpot_username",
        "PENPOT_PASSWORD": "your_penpot_password"
      }
    }
  }
}

Tools

10

Retrieve a list of all available Penpot projects.

Get all files contained within a specific Penpot project. Args: project_id: The ID of the Penpot project

Retrieve a Penpot file by its ID and cache it. Don't use this tool for code generation, use 'get_object_tree' instead. Args: file_id: The ID of the Penpot file

Export a Penpot design object as an image. Args: file_id: The ID of the Penpot file page_id: The ID of the page containing the object object_id: The ID of the object to export export_type: Image format (png, svg, etc.) scale: Scale factor for the exported image

Get the object tree structure for a Penpot object ("tree" field) with rendered screenshot image of the object ("image.mcp_uri" field). Args: file_id: The ID of the Penpot file object_id: The ID of the object to retrieve fields: Specific fields to include in the tree (call "penpot_tree_schema" resource/tool for available fields) depth: How deep to traverse the object tree (-1 for full depth) format: Output format ('json' or 'yaml')

Search for objects within a Penpot file by name. Args: file_id: The ID of the Penpot file to search in query: Search string (supports regex patterns)

Provide the Penpot API schema as JSON.

Provide the Penpot object tree schema as JSON.

Return a rendered component image by its ID.

List all files currently stored in the cache.

Overview

What is Penpot MCP?

Penpot MCP is a Model Context Protocol (MCP) server that connects AI language models (like Claude) with the Penpot open-source design and prototyping platform. It enables AI-powered design analysis, automation, and natural language interaction with Penpot files.

How to use Penpot MCP?

Install via pip install penpot-mcp or uvx penpot-mcp, then run penpot-mcp or uv run penpot-mcp. Configure a .env file with Penpot API credentials (PENPOT_API_URL, PENPOT_USERNAME, PENPOT_PASSWORD). Integrate with Claude Desktop or Cursor IDE by adding the server’s MCP configuration.

Key features of Penpot MCP

  • Full MCP protocol compliance
  • Direct real-time access to Penpot API
  • AI-powered design component analysis
  • Automated export of assets in multiple formats
  • Design system compliance validation
  • Native Claude Desktop and Cursor IDE integration

Use cases of Penpot MCP

  • Automate design reviews with instant AI feedback on accessibility and usability
  • Generate documentation for design systems automatically
  • Check brand guideline compliance across projects
  • Bridge design-to-code workflows with AI assistance
  • Track design system adoption and component usage analytics

FAQ from Penpot MCP

What are the prerequisites to use Penpot MCP?

Python 3.12+, a Penpot account, and optionally Claude Desktop or Cursor IDE for AI integration.

Where do I put my Penpot credentials?

Create a .env file with PENPOT_API_URL, PENPOT_USERNAME, and PENPOT_PASSWORD variables.

What MCP tools are available?

Tools include list_projects, get_project_files, get_file, export_object, get_object_tree, and search_object.

How do I integrate with Claude Desktop?

Add the MCP server configuration (command, args, env) to Claude Desktop’s config file (claude_desktop_config.json).

Can I run the server locally from source?

Yes, clone the repository, create a virtual environment, and install with pip install -e . or uv sync.

Comments

More Developer Tools MCP servers