Cursor Talk to Figma MCP
Uses Bun as the JavaScript runtime for the MCP server, allowing it to run the WebSocket server that facilitates communication between Cursor AI and the Figma plugin.
Enables communication with Figma for reading design information and modifying designs programmatically. Includes tools for document inspection, annotation management, element creation, text content modification, styling adjustments, layout organization, component handling, and exporting designs as images.
Implements the MCP server in TypeScript, providing type safety and better developer experience for interacting with Figma's API.
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., "@Cursor Talk to Figma MCP scan text nodes in the current selection and show me the first 5 results"
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.
Cursor Talk to Figma MCP
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
https://github.com/user-attachments/assets/129a14d2-ed73-470f-9a4c-2240b2a4885c
Project Structure
src/talk_to_figma_mcp/- TypeScript MCP server for Figma integrationsrc/cursor_mcp_plugin/- Figma plugin for communicating with Cursorsrc/socket.ts- WebSocket server that facilitates communication between the MCP server and Figma plugin
Related MCP server: Figma MCP Server
Get Started
Install Bun if you haven't already:
curl -fsSL https://bun.sh/install | bashRun setup, this will also install MCP in your Cursor's active project
bun setupStart the Websocket server
bun socketMCP server
bunx cursor-talk-to-figma-mcpInstall Figma Plugin
Quick Video Tutorial
Design Automation Example
Bulk text content replacement
Thanks to @dusskapark for contributing the bulk text replacement feature. Here is the demo video.
Manual Setup and Installation
MCP Server: Integration with Cursor
Add the server to your Cursor MCP configuration in ~/.cursor/mcp.json:
{
"mcpServers": {
"TalkToFigma": {
"command": "bunx",
"args": ["cursor-talk-to-figma-mcp@latest"]
}
}
}WebSocket Server
Start the WebSocket server:
bun socketFigma Plugin
In Figma, go to Plugins > Development > New Plugin
Choose "Link existing plugin"
Select the
src/cursor_mcp_plugin/manifest.jsonfileThe plugin should now be available in your Figma development plugins
Windows + WSL Guide
Install bun via powershell
powershell -c "irm bun.sh/install.ps1|iex"Uncomment the hostname
0.0.0.0insrc/socket.ts
// uncomment this to allow connections in windows wsl
hostname: "0.0.0.0",Start the websocket
bun socketUsage
Start the WebSocket server
Install the MCP server in Cursor
Open Figma and run the Cursor MCP Plugin
Connect the plugin to the WebSocket server by joining a channel using
join_channelUse Cursor to communicate with Figma using the MCP tools
MCP Tools
The MCP server provides the following tools for interacting with Figma:
Document & Selection
get_document_info- Get information about the current Figma documentget_selection- Get information about the current selectionread_my_design- Get detailed node information about the current selection without parametersget_node_info- Get detailed information about a specific nodeget_nodes_info- Get detailed information about multiple nodes by providing an array of node IDs
Annotations
get_annotations- Get all annotations in the current document or specific nodeset_annotation- Create or update an annotation with markdown supportset_multiple_annotations- Batch create/update multiple annotations efficientlyscan_nodes_by_types- Scan for nodes with specific types (useful for finding annotation targets)
Creating Elements
create_rectangle- Create a new rectangle with position, size, and optional namecreate_frame- Create a new frame with position, size, and optional namecreate_text- Create a new text node with customizable font properties
Modifying text content
scan_text_nodes- Scan text nodes with intelligent chunking for large designsset_text_content- Set the text content of a single text nodeset_multiple_text_contents- Batch update multiple text nodes efficiently
Styling
set_fill_color- Set the fill color of a node (RGBA)set_stroke_color- Set the stroke color and weight of a nodeset_corner_radius- Set the corner radius of a node with optional per-corner control
Layout & Organization
move_node- Move a node to a new positionresize_node- Resize a node with new dimensionsdelete_node- Delete a nodedelete_multiple_nodes- Delete multiple nodes at once efficientlyclone_node- Create a copy of an existing node with optional position offset
Components & Styles
get_styles- Get information about local stylesget_local_components- Get information about local componentscreate_component_instance- Create an instance of a component
Export & Advanced
export_node_as_image- Export a node as an image (PNG, JPG, SVG, or PDF) - limited support on image currently returning base64 as text
Connection Management
join_channel- Join a specific channel to communicate with Figma
Development
Building the Figma Plugin
Navigate to the Figma plugin directory:
cd src/cursor_mcp_pluginEdit code.js and ui.html
Best Practices
When working with the Figma MCP:
Always join a channel before sending commands
Get document overview using
get_document_infofirstCheck current selection with
get_selectionbefore modificationsUse appropriate creation tools based on needs:
create_framefor containerscreate_rectanglefor basic shapescreate_textfor text elements
Verify changes using
get_node_infoUse component instances when possible for consistency
Handle errors appropriately as all commands can throw exceptions
For large designs:
Use chunking parameters in
scan_text_nodesMonitor progress through WebSocket updates
Implement appropriate error handling
For text operations:
Use batch operations when possible
Consider structural relationships
Verify changes with targeted exports
For converting legacy annotations:
Scan text nodes to identify numbered markers and descriptions
Use
scan_nodes_by_typesto find UI elements that annotations refer toMatch markers with their target elements using path, name, or proximity
Categorize annotations appropriately with
get_annotationsCreate native annotations with
set_multiple_annotationsin batchesVerify all annotations are properly linked to their targets
Delete legacy annotation nodes after successful conversion
License
MIT
Available Tools
33 toolsclone_nodeB
Clone an existing node in Figma
Inputs: nodeId (required), x, y.
create_component_instanceC
Create an instance of a component in Figma
Inputs: componentKey (required), x (required), y (required).
create_frameC
Create a new frame in Figma
Inputs: x (required), y (required), width (required), height (required), +16 more.
create_rectangleB
Create a new rectangle in Figma
Inputs: x (required), y (required), width (required), height (required), +2 more.
create_textB
Create a new text element in Figma
Inputs: x (required), y (required), text (required), fontSize, +4 more.
delete_multiple_nodesA
Delete multiple nodes from Figma at once
Inputs: nodeIds (required).
delete_nodeC
Delete a node from Figma
Inputs: nodeId (required).
export_node_as_imageB
Export a node as an image from Figma
Inputs: nodeId (required), format, scale.
get_annotationsA
Get all annotations in the current document or specific node
Inputs: nodeId, includeCategories.
get_document_infoB
Get detailed information about the current Figma document
Inputs: no named parameters.
get_local_componentsA
Get all local components from the Figma document
Inputs: no named parameters.
get_node_infoB
Get detailed information about a specific node in Figma
Inputs: nodeId (required).
get_nodes_infoA
Get detailed information about multiple nodes in Figma
Inputs: nodeIds (required).
get_selectionB
Get information about the current selection in Figma
Inputs: no named parameters.
get_stylesA
Get all styles from the current Figma document
Inputs: no named parameters.
join_channelB
Join a specific channel to communicate with Figma
Inputs: channel.
move_nodeA
Move a node to a new position in Figma
Inputs: nodeId (required), x (required), y (required).
read_my_designA
Get detailed information about the current selection in Figma, including all node details
Inputs: no named parameters.
resize_nodeC
Resize a node in Figma
Inputs: nodeId (required), width (required), height (required).
scan_nodes_by_typesC
Scan for nodes with specific types in the selected Figma node
Inputs: nodeId (required), types (required).
scan_text_nodesB
Scan all text nodes in the selected Figma node
Inputs: nodeId (required).
set_annotationC
Create or update an annotation
Inputs: nodeId (required), labelMarkdown (required), annotationId, categoryId, +1 more.
set_axis_alignA
Set primary and counter axis alignment for an auto-layout frame in Figma
Inputs: nodeId (required), primaryAxisAlignItems, counterAxisAlignItems.
set_corner_radiusA
Set the corner radius of a node in Figma
Inputs: nodeId (required), radius (required), corners.
set_fill_colorC
Set the fill color of a node in Figma can be TextNode or FrameNode
Inputs: nodeId (required), r (required), g (required), b (required), +1 more.
set_item_spacingA
Set distance between children in an auto-layout frame
Inputs: nodeId (required), itemSpacing (required).
set_layout_modeB
Set the layout mode and wrap behavior of a frame in Figma
Inputs: nodeId (required), layoutMode (required), layoutWrap.
set_layout_sizingB
Set horizontal and vertical sizing modes for an auto-layout frame in Figma
Inputs: nodeId (required), layoutSizingHorizontal, layoutSizingVertical.
set_multiple_annotationsC
Set multiple annotations parallelly in a node
Inputs: nodeId (required), annotations (required).
set_multiple_text_contentsC
Set multiple text contents parallelly in a node
Inputs: nodeId (required), text (required).
set_paddingA
Set padding values for an auto-layout frame in Figma
Inputs: nodeId (required), paddingTop, paddingRight, paddingBottom, +1 more.
set_stroke_colorB
Set the stroke color of a node in Figma
Inputs: nodeId (required), r (required), g (required), b (required), +2 more.
set_text_contentA
Set the text content of an existing text node in Figma
Inputs: nodeId (required), text (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 33 tools
Most tools have distinct purposes, but some overlap exists. For example, 'get_selection' and 'read_my_design' both retrieve selection information, and 'get_node_info' vs 'get_nodes_info' are similar but for single vs multiple nodes. Descriptions help clarify, but an agent might occasionally misselect between closely related tools.
Tool names follow a consistent snake_case verb_noun pattern throughout, such as 'create_frame', 'delete_node', and 'set_fill_color'. The naming is predictable and readable, with no deviations in style or convention across all 33 tools.
With 33 tools, the count is too high for a typical MCP server, making it feel heavy and potentially overwhelming. While Figma is a complex domain, this many tools suggests fragmentation rather than a well-scoped set, which could hinder agent usability.
The tool set covers a wide range of Figma operations, including creation, deletion, modification, and querying of nodes, with good lifecycle coverage. Minor gaps exist, such as no explicit tool for updating node properties beyond specific setters or handling component overrides, but agents can likely work around these.
Maintenance
Related MCP Connectors
The Figma MCP server brings Figma design context directly into your AI workflow.
Access and maintain design system docs, tokens, components, skills, and contexts across any project.
Serves your design system and coding standards to coding agents, so they stop guessing.
A Model Context Protocol server for Wix AI tools
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables seamless interaction with Figma via the Model Context Protocol, allowing LLM applications to access, manipulate, and track Figma files, components, and variables.2149-
- AlicenseNot gradedqualityCmaintenanceEnables Cursor to access Figma files through the Model Context Protocol, enhancing its ability to accurately interpret and utilize design data for code generation.151,155 npm16,266MIT
- AlicenseBqualityDmaintenanceAllows Cursor AI to communicate with Figma for reading designs and modifying them programmatically through a Model Context Protocol integration.381MIT
- FlicenseBqualityDmaintenanceEnables Cursor AI to read and modify Figma designs programmatically via the Model Context Protocol.383-