What it does

Reads variables, styles, and component trees from Figma and can write changes back. The token extraction is the useful half; the write half needs a scoped token and a healthy respect for designers' files. Pair with a code-generation workflow rather than using it as a design reviewer.

Install

Terminal

npx -y figma-console-mcp

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "figma-console": {
      "command": "npx",
      "args": [
        "-y",
        "figma-console-mcp"
      ]
    }
  }
}

Use it for

Pulling design tokens and component structure out of a Figma file

Skip it if

Screenshot-driven visual comparison

When to use it

Reach for this when the task needs figma inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Figma Console MCP