Server profile

Framelink MCP for Figma

Framelink supplies coding agents with selected Figma metadata and image assets. Developers can bring a design link into an editor conversation and use its underlying layout details while implementing an interface.

Server facts

Framelink MCP for Figma

Tech

Runtime / language
nodeTypeScript
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
15,999
Last commit
Data as of

Tags

  • Cursor
  • Design Assets
  • Design Context
  • Figma
  • Typescript

Overview

A screenshot leaves a coding assistant to interpret the visual result; Framelink instead retrieves metadata behind the design. The server processes responses from Figma's API, narrowing the material to layout decisions and styling details useful during implementation. This filtering is central to the project's approach: the assistant receives a smaller design context rather than an unmodified API response. The README centers its examples on Cursor, although the configuration discussion also addresses other editors and assistant clients. A developer starts the interaction by sharing a design link in chat and requesting work based on it, such as building the corresponding interface. Links can identify a group, an individual frame, or the broader file.

The supplied inventory divides access into two operations. One retrieves design structure, including file-wide layout when a node identifier is missing. The other fetches image assets by their node identifiers, with SVG and PNG output described. Access depends on a personal Figma token, not just possession of the shared link. For local use, the README launches the figma-developer-mcp package with stdio enabled. It gives separate shell arrangements for Windows and Unix-like systems, and permits credentials through either an argument or an environment setting. Additional configuration guidance lives in the linked Framelink quickstart. Together, the metadata and asset paths address distinct parts of implementing a linked design.

Install & configure

Requirements

  • Personal access token issued by Figma
  • npx available to the client process
  • Editor or assistant with MCP support
Documented launch / install command
npx -y figma-developer-mcp --figma-api-key=YOUR-KEY --stdio

The argument array reproduces the macOS/Linux README example, including its YOUR-KEY marker; substitute your token. Windows adds cmd /c around npx. As an alternative to the inline token, the README permits FIGMA_API_KEY in env and also mentions PORT.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "Figma-Context-MCP": {
      "command": "npx",
      "args": [
        "-y",
        "figma-developer-mcp",
        "--figma-api-key=YOUR-KEY",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "Figma-Context-MCP": {
      "command": "npx",
      "args": [
        "-y",
        "figma-developer-mcp",
        "--figma-api-key=YOUR-KEY",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "Figma-Context-MCP": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "figma-developer-mcp",
        "--figma-api-key=YOUR-KEY",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "Figma-Context-MCP": {
      "command": "npx",
      "args": [
        "-y",
        "figma-developer-mcp",
        "--figma-api-key=YOUR-KEY",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "Figma-Context-MCP": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "figma-developer-mcp",
        "--figma-api-key=YOUR-KEY",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
download_figma_imagesFetch design assets as PNG or SVG by specifying image or icon nodes.
get_figma_dataInspect design layout; a missing node ID can be handled by retrieving file-wide information.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Give an implementation request the layout metadata behind a shared design link.
  • Inspect file-wide structure when the requested design has no known node identifier.
  • Fetch icon or image nodes as assets for the interface being built.
  • Use a Cursor chat to connect Figma styling decisions with application code.

Strengths

  • Filters the API response before placing design details in the model's context.
  • Pairs structural lookup with a separate route for retrieving visual assets.
  • Shows native npx configuration alongside a Windows shell variant.

Limitations

  • A personal Figma credential is necessary even when a design link is available.
  • Cursor receives the detailed workflow treatment; other clients are discussed more generally.

Frequently asked questions

It comes from Figma metadata rather than image interpretation. Framelink trims the API response around implementation-relevant styling and layout.

No. The documented chat workflow can begin with a group or frame link as well as a file link.

The supplied image tool uses node IDs for icons or images and supports PNG and SVG downloads.

Yes. The README names FIGMA_API_KEY as an environment-based alternative to passing the token inline.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

21st.dev Magic AI Agent

Design & Creative

21st.dev Magic AI Agent turns natural-language requests into customizable UI components inside supported coding tools. It combines component-library inspiration, previews, TypeScript support, and brand assets for interface development.

DaVinci Resolve MCP Server

Design & Creative

Control DaVinci Resolve Studio from an AI assistant through its scripting API. Editing, grading, media analysis, render preparation, and a local control panel support post-production workflows.

FreeCAD MCP

Design & Creative

Control FreeCAD from an assistant through an addon and Python MCP server. Tools create and inspect CAD objects, run Python, use library parts, capture views, and execute existing FEM analyses.

Photoshop MCP Server

Design & Creative

Photoshop MCP Server lets assistants control a locally installed Photoshop through photoshop-python-api. It supports document work, layers, and session inspection on Windows only.

Draw.io MCP Server

Design & Creative

Draw.io MCP Server gives assistants control over diagrams in a browser. It can host its own editor or connect through an extension, with explicit document and page selection for larger diagramming sessions.

After Effects MCP Server

Design & Creative

After Effects MCP Server routes assistant commands into an open Adobe After Effects session. A bridge panel enables composition and layer work, animation controls, and JavaScript execution inside the application.