The MCP server acts as a bidirectional bridge between AI assistants and Figma, allowing them to draw UI directly on the Figma canvas and read existing designs as structured data, screenshots, or code-ready tokens.
From the registry: Bidirectional Figma MCP — AI draws UI on Figma canvas, reads designs back
Please install the `figma-ui-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Figma Desktop app** — Figma Desktop is required (web app cannot access localhost) (https://www.figma.com/downloads/)
- **Install the Figma plugin** — Install the companion Figma plugin that polls the local MCP server (https://github.com/TranHoaiHung/figma-ui-mcp)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","figma-ui-mcp"]
Note: No Figma API key required — uses a localhost HTTP bridge (port 38451) with the plugin.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.