Skip to content
Back to search

figma-mcp

ModelContextProtocol for Figma's REST API

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/matthewdailey--figma-mcp/badge.svg)](/listings/matthewdailey--figma-mcp)

HTML

<a href="/listings/matthewdailey--figma-mcp"><img src="/api/listings/matthewdailey--figma-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Installing via Smithery

To install Figma MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@MatthewDailey/figma-mcp):

npx -y @smithery/cli install @MatthewDailey/figma-mcp --client claude

1. Download and install Claude desktop app from [claude.ai/download](https://claude.ai/download)

2. Get a Figma API Key (figma.com -> click your name top left -> settings -> Security). Grant `File content` and `Comments` scopes.

2. Configure Claude to use the Figma MCP server. If this is your first MCP server, run the following in terminal.

echo '{
  "mcpServers": {
    "figma-mcp": {
      "command": "npx",
      "args": ["figma-mcp"],
      "env": {
        "FIGMA_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}' > ~/Library/Application\ Support/Claude/claude_desktop_config.json

If it's not, copy the `figma-mcp` block to your `claude_desktop_config.json`

3. Restart Claude Desktop.

4. Look for the hammer icon with the number of available tools in Claude's interface to confirm the server is running.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 100 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Figma MCP Server
  2. [![smithery badge](https://smithery.ai/badge/@MatthewDailey/figma-mcp)](https://smithery.ai/server/@MatthewDailey/figma-mcp)
  3. A [ModelContextProtocol](https://modelcontextprotocol.io) server that enables AI assistants to interact with Figma files. This server provides tools for viewing, commenting, and analyzing Figma designs directly through the ModelContextProtocol.
  4. ## Features
  5. - Add a Figma file to your chat with Claude by providing the url
  6. - Read and post comments on Figma files
  7. ## Setup with Claude
  8. ### Installing via Smithery
  9. To install Figma MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@MatthewDailey/figma-mcp):
  10. ```bash
  11. npx -y @smithery/cli install @MatthewDailey/figma-mcp --client claude
  12. ```
  13. 1. Download and install Claude desktop app from [claude.ai/download](https://claude.ai/download)
  14. 2. Get a Figma API Key (figma.com -> click your name top left -> settings -> Security). Grant `File content` and `Comments` scopes.
  15. 2. Configure Claude to use the Figma MCP server. If this is your first MCP server, run the following in terminal.
  16. ```bash
  17. echo '{
  18. "mcpServers": {
  19. "figma-mcp": {
  20. "command": "npx",
  21. "args": ["figma-mcp"],
  22. "env": {
  23. "FIGMA_API_KEY": "<YOUR_API_KEY>"
  24. }
  25. }
  26. }
  27. }' > ~/Library/Application\ Support/Claude/claude_desktop_config.json
  28. ```
  29. If it's not, copy the `figma-mcp` block to your `claude_desktop_config.json`
  30. 3. Restart Claude Desktop.
  31. 4. Look for the hammer icon with the number of available tools in Claude's interface to confirm the server is running.
  32. ## Example usage
  33. Start a new chat with claude desktop and paste the following
  34. ```
  35. What's in this figma file?
  36. https://www.figma.com/design/MLkM98c1s4A9o9CMnHEyEC
  37. ```
  38. ## Demo of a more realistic usage
  39. https://www.loom.com/share/0e759622e05e4ab1819325bcf6128945?sid=bcf6125b-b5de-4098-bf81-baff157e3dc3
  40. ## Development Setup
  41. ### Running with Inspector
  42. For development and debugging purposes, you can use the MCP Inspector tool. The Inspector provides a visual interface for testing and monitoring MCP server interactions.
  43. Visit the [Inspector documentation](https://modelcontextprotocol.io/docs/tools/inspector) for detailed setup instructions and usage guidelines.
  44. The command to test locally with Inspector is
  45. ```
  46. npx @modelcontextprotocol/inspector npx figma-mcp
  47. ```
  48. ### Local Development
  49. 1. Clone the repository
  50. 2. Install dependencies:
  51. ```bash
  52. npm install
  53. ```
  54. 3. Build the project:
  55. ```bash
  56. npm run build
  57. ```
  58. 4. For development with auto-rebuilding:
  59. ```bash
  60. npm run watch
  61. ```
  62. ## Available Tools
  63. The server provides the following tools:
  64. - `add_figma_file`: Add a Figma file to your context by providing its URL
  65. - `view_node`: Get a thumbnail for a specific node in a Figma file
  66. - `read_comments`: Get all comments on a Figma file
  67. - `post_comment`: Post a comment on a node in a Figma file
  68. - `reply_to_comment`: Reply to an existing comment in a Figma file
  69. Each tool is designed to provide specific functionality for interacting with Figma files through the ModelContextProtocol interface.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.