Framelink MCP for Figma provides AI coding agents access to Figma design data through the Model Context Protocol, enabling them to fetch and parse design metadata directly from Figma files, frames, and groups. The server simplifies Figma API responses by extracting only relevant layout and styling information, reducing context noise to improve AI accuracy when implementing designs. This integration allows tools like Cursor to generate code implementations of UI designs in a single pass by accessing structured design data instead of relying on screenshots.
claude mcp add figma-context-mcp --env FIGMA_API_KEY=YOUR_FIGMA_API_KEY -- npx -y figma-developer-mcp --stdioRun in your terminal. Replace YOUR_* placeholders with real values; add --scope user to install for every project.
Review the command, arguments, and environment values before installing — MCP servers run with your local permissions.
Verified live against the running server on Jun 10, 2026.
get_figma_dataGet comprehensive Figma file data including layout, content, visuals, and component information3 paramsGet comprehensive Figma file data including layout, content, visuals, and component information
depthnumbernodeIdstringfileKey*stringdownload_figma_imagesDownload SVG and PNG images used in a Figma file based on the IDs of image or icon nodes. Images will be saved relative to the server's image directory: /Users/duzgundev/code/vinena-studio/claudemarketplaces.com.feat-directory-quality4 paramsDownload SVG and PNG images used in a Figma file based on the IDs of image or icon nodes. Images will be saved relative to the server's image directory: /Users/duzgundev/code/vinena-studio/claudemarketplaces.com.feat-directory-quality
nodes*arrayfileKey*stringpngScalenumberlocalPath*string
Give Cursor and other AI-powered coding tools 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.
Watch a demo of building a UI in Cursor with Figma design data
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.
Many code editors and other AI clients use a configuration file to manage MCP servers.
The figma-developer-mcp server can be configured by adding the following to your configuration file.
NOTE: You will need to create a Figma access token to use this server. Instructions on how to create a Figma API access token can be found here.
{
"mcpServers": {
"Framelink MCP for Figma": {
"command": "npx",
"args": ["-y", "figma-developer-mcp", "--figma-api-key=YOUR-KEY", "--stdio"]
}
}
}
{
"mcpServers": {
"Framelink MCP for Figma": {
"command": "cmd",
"args": ["/c", "npx", "-y", "figma-developer-mcp", "--figma-api-key=YOUR-KEY", "--stdio"]
}
}
}
Or you can set FIGMA_API_KEY and PORT in the env field.
If you need more information on how to configure the Framelink MCP for Figma, see the Framelink docs.
The Framelink MCP for Figma is simple but powerful. Get the most out of it by learning more at the Framelink site.
FIGMA_API_KEY*secretYour Figma Personal Access Token, learn more here: https://www.figma.com/developers/api#access-tokens
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent