Penpot MCP Server
Provides tools for retrieving Penpot boards, debugging board data, and extracting design tokens from Penpot files.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Penpot MCP Server get design tokens from https://design.penpot.app/file/abc123"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Penpot MCP Server
A Model Context Protocol (MCP) server for integrating Penpot with AI assistants.
Installation & Publishing
For development
npm install
npm startFor publishing to npm
npm publishFor users (via npx)
No installation needed - use directly with npx in your MCP configuration.
Related MCP server: F-MCP (Figma MCP Bridge)
Configuration
Penpot Configuration
To use the Penpot API, you need to configure:
Access Token: Log in to Penpot → Profile → Access tokens → Create new token
API URL (optional): For self-hosted Penpot instances
Add both to your MCP configuration environment variables:
PENPOT_ACCESS_TOKEN: Your access tokenPENPOT_API_URL: API base URL (defaults tohttps://design.penpot.app/api)
Available Tools
get_board
Retrieves a Penpot board.
Parameters:
url(string, required): Complete Penpot board URL withboard-id
Returns: HTML, JSON object, tokens used, and CSS variables
debug_board
Retrieves a Penpot board and displays the raw JSON for debugging.
Parameters:
url(string, required): Complete Penpot board URL withboard-id
get_tokens
Retrieves design tokens from a Penpot file.
Parameters:
url(string, required): Complete Penpot file URL (only needsfile-id)
Returns: DTCG formatted tokens, CSS variables, and summary
Project Structure
penpot-mcp/
├── index.js # Main server
├── src/
│ └── tools/
│ ├── get-board.js # get_board tool
│ ├── debug-board.js # debug_board tool
│ └── get-tokens.js # get_tokens tool
├── package.json
└── README.mdMCP Client Configuration
Add this configuration to your MCP client:
{
"mcpServers": {
"penpot": {
"command": "npx",
"args": [
"-y",
"penpot-mcp-server@latest"
],
"env": {
"PENPOT_ACCESS_TOKEN": "your_penpot_token_here",
"PENPOT_API_URL": "https://design.penpot.app/api"
}
}
}
}Or for local development:
{
"mcpServers": {
"penpot": {
"command": "node",
"args": ["/path/to/penpot-mcp/index.js"],
"env": {
"PENPOT_ACCESS_TOKEN": "your_penpot_token_here",
"PENPOT_API_URL": "https://design.penpot.app/api"
}
}
}
}Available Tools
3 toolsdebug_boardA
Retrieves a Penpot board and displays raw JSON for debugging
Inputs: url (required).
get_boardB
Retrieves a Penpot board and converts it to Tailwind CSS code
Inputs: url (required).
get_tokensA
Retrieves design tokens from a Penpot file and formats them according to DTCG standard
Inputs: url (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: debug_board returns raw JSON, get_board converts to Tailwind CSS, and get_tokens retrieves design tokens. No ambiguity between them.
All tool names follow verb_noun pattern (debug_board, get_board, get_tokens), but one uses 'debug' while the other two use 'get', showing slight inconsistency in verb choice.
Three tools is on the lower side but still reasonable for a focused server. It covers core retrieval operations without being overly minimal.
The tool surface covers board retrieval and token extraction but lacks operations like listing files, projects, or creating/updating content, which are notable gaps for a design server.
Maintenance
Related MCP Connectors
Give AI agents your deeepSpace design system: components, tokens, styles and code mappings.
1Gives AI agents direct access to your Sanity projects and guidance for working with them
Web search, data extraction and controlled browser automation for AI assistants via OAuth.
Secure AI access to OpenOak tasks, notes, and Kanban boards.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to programmatically access self-hosted Penpot instances to read, create, modify, and export design elements through natural language. It provides 66 tools for managing projects, shapes, design tokens, and comments using a dual-access strategy of direct database reads and RPC API writes.12Apache 2.0
- AlicenseBqualityBmaintenanceEnables AI assistants to read, analyze, and modify Figma designs, manage design tokens, and create prototype connections, all while keeping data local.6344 npm10MIT
- AlicenseCqualityDmaintenanceEnables AI assistants to create, modify, and manage Penpot designs programmatically, providing full manipulation capabilities for the open-source design tool.8154 npm20MIT
- AlicenseNot gradedqualityFmaintenanceEnables LLMs to query, transform, and create design elements in Penpot via the Model Context Protocol and Penpot's Plugin API.535Mozilla Public 2.0