Skip to main content
Glama
Knightwxch

Figma MCP Server

by Knightwxch

Figma MCP Server

Give Cursor access to your Figma files with this Model Context Protocol server.

When Cursor has access to Figma design data, it's way better at one-shotting designs accurately than alternative approaches like pasting screenshots.

Demo Video

Watch a demo of building a UI in Cursor with Figma design data Watch the video

Related MCP server: Talk to Figma MCP

How it works

  1. Open Cursor's composer in agent mode.

  2. Paste a link to a Figma file, frame, or group.

  3. Ask Cursor to do something with the Figma fileβ€”e.g. implement a design.

  4. Cursor will fetch the relevant metadata from Figma and use it to write your code.

This MCP server is specifically designed for use with Cursor. Before responding with context from the Figma API, it simplifies and translates the response so only the most relevant layout and styling information is provided to the model.

Reducing the amount of context provided to the model helps make the AI more accurate and the responses more relevant.

Installation

  1. Clone the repository

  2. Install dependencies with pnpm install

  3. Copy .env.example to .env and fill in your Figma API access token. Only read access is required.

Connecting to Cursor

Start the development server

> pnpm dev
# Initializing Figma MCP Server in HTTP mode on port 3333...
# HTTP server listening on port 3333
# SSE endpoint available at http://localhost:3333/sse
# Message endpoint available at http://localhost:3333/messages

Connect Cursor to the MCP server

Once the server is running, connect Cursor to the MCP server in Cursor's settings, under the features tab.

Connecting to MCP server in Cursor

After the server has been connected, you can confirm Cursor's has a valid connection before getting started. If you get a green dot and the tools show up, you're good to go!

Confirming connection in Cursor

Start using Composer with your Figma designs

Once the MCP server is connected, you can start using the tools in Cursor's composer, as long as the composer is in agent mode.

Dropping a link to a Figma file in the composer and asking Cursor to do something with it should automatically trigger the get-file tool.

Most Figma files end up being huge, so you'll probably want to link to a specific frame or group within the file. With a single element selected, you can hit CMD + L to copy the link to the element. You can also find it in the context menu:

Copy link to Figma selection by right clicking

Once you have a link to a specific element, you can drop it in the composer and ask Cursor to do something with it.

Inspect Responses

To inspect responses from the MCP server more easily, you can run the inspect command, which launches the @modelcontextprotocol/inspector web UI for triggering tool calls and reviewing responses:

pnpm inspect
# > figma-mcp@0.1.0 inspect
# > pnpx @modelcontextprotocol/inspector
#
# Starting MCP inspector...
# Proxy server listening on port 3000
#
# πŸ” MCP Inspector is up and running at http://localhost:5173 πŸš€

Available Tools

The server provides the following MCP tools:

get-file

Fetches information about a Figma file.

Parameters:

  • fileKey (string): The key of the Figma file to fetch

  • depth (number, optional): How many levels deep to traverse the node tree

get-node

Fetches information about a specific node within a Figma file.

Parameters:

  • fileKey (string): The key of the Figma file containing the node

  • nodeId (string): The ID of the node to fetch

Related MCP Connectors

  • The Figma MCP server brings Figma design context directly into your AI workflow.

  • The Canva MCP server connects AI assistants (like Claude, ChatGPT, and Cursor) to Canva's API, enabling them to create and manage designs directly within chat conversations. Key capabilities include generating new designs from prompts, autofilling templates, searching and resizing existing designs, importing files from URLs, exporting designs as PDFs or images, and managing folders and comments without switching between tools.

  • Connect AI agents to Filepad workspaces through OAuth MCP.

  • Run, debug, and triage tests from your IDE using natural language, no dashboard switching, no manual data transfers. The TestMu AI (formerly LambdaTest) MCP Server is a single remote server exposing four tool suites: HyperExecute β€” analyze your project, generate YAML configs and test runner commands, then monitor jobs and sessions. Automation β€” pull a TestID's details plus command, network, and console logs into one chat for instant root-cause analysis. Includes mobile app upload. SmartUI β€” explain pixel, layout, DOM, and perceptual changes in a visual regression run, with context-aware React/HTML/CSS fixes. Accessibility β€” audit any public URL or a local React app against WCAG and get ready-to-apply remediation steps. Connects over https://mcp.lambdatest.com/mcp using OAuth 2.1 β€” no API keys in your config. One-click install in Cursor; works with Claude, GitHub Copilot, Cline, and any MCP client. Tests execute on the TestMu AI cloud: 3,000+ browsers and 10,000+ real devices.

Related MCP Servers