figma_mcp

kdoronin/figma_mcp

3.4

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.

Tools

Functions exposed to the LLM to take actions

join_channel

Join a channel for communication with Figma.

get_document_info

Retrieve information about the current Figma document.

get_selection

Get information about the current selection.

read_my_design

Get detailed information about the selection including all node details.

get_node_info

Retrieve information about a specific node by ID.

get_nodes_info

Retrieve information about multiple nodes.

get_node_children

Get IDs of all child nodes with full recursive nesting.

get_styles

Retrieve all styles from the document.

get_local_components

Retrieve all local components.

get_instance_overrides

Get instance overrides of a component.

scan_text_nodes

Scan text nodes within a specified node.

scan_nodes_by_types

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

export_node_as_image

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

get_annotations

Retrieve annotations for a node or the entire document.

get_reactions

Get reactions (interactive links) for nodes.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources