figma_mcp

figma_mcp

3.3

If you are the rightful owner of figma_mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Figma Model Context Protocol (MCP) server implemented in Python using FastMCP, enabling AI assistants to interact with Figma via WebSocket for data reading and design analysis.

The Figma MCP Server is a Python-based server that leverages the FastMCP framework to facilitate interaction between AI assistants and Figma. This server allows for seamless communication through WebSocket connections, enabling the retrieval and analysis of design data from Figma documents. It is designed to provide comprehensive access to document information, node details, and component interactions, while maintaining a secure environment by restricting modification capabilities. The server architecture includes an MCP Server, a WebSocket Server, and a Figma Plugin, ensuring efficient coordination and execution of commands within Figma. With a focus on reading and exporting data, the server supports various tools for scanning, exporting, and annotating design elements, making it a valuable resource for AI-driven design analysis and prototyping.

Features

  • Data Reading: Retrieve information about documents, nodes, components, and styles.
  • Search and Analysis: Scan nodes by types and search for text content.
  • Export: Export nodes as images in various formats.
  • Annotations: View annotations in documents.
  • Components: Work with components and their instances.

Tools

  1. join_channel

    Join a channel for communication with Figma.

  2. get_document_info

    Retrieve information about the current Figma document.

  3. get_selection

    Get information about the current selection.

  4. read_my_design

    Get detailed information about the selection including all node details.

  5. get_node_info

    Retrieve information about a specific node by ID.

  6. get_nodes_info

    Retrieve information about multiple nodes.

  7. get_node_children

    Get IDs of all child nodes with full recursive nesting.

  8. get_styles

    Retrieve all styles from the document.

  9. get_local_components

    Retrieve all local components.

  10. get_instance_overrides

    Get instance overrides of a component.

  11. scan_text_nodes

    Scan text nodes within a specified node.

  12. scan_nodes_by_types

    Scan nodes of specific types (TEXT, RECTANGLE, FRAME).

  13. export_node_as_image

    Export a node as an image (PNG, JPG, SVG, PDF).

  14. get_annotations

    Retrieve annotations for a node or the entire document.

  15. get_reactions

    Get reactions (interactive links) for nodes.