Skip to content
Custom Connectors
SolutionsConnectorsPricingResourcesBlog
Build my connector

Connect Figma to Claude Code

Let Claude comment and manage variables in Figma. From the terminal, inside the sessions where you already work.

Build my connectorTalk to us

How do you connect Figma to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Figma, you add a Figma MCP server: a small hosted service that exposes Figma's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Figma account. No API keys pasted into config files.

claude mcp add --transport http figma https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Figma once connected?

A custom REST Figma connector lets Claude fetch file and node details, list comments, post and reply to comments pinned to specific frames, and read or update variables once you approve. The comment review and variable bookkeeping that used to mean manual clicking happen through scoped, approval-gated tools instead.

  • Post a comment pinned to a specific frame or node
  • Reply to existing comments during a design review
  • Fetch a file and read its nodes, layout, and properties
  • Summarize unresolved comments across a file before a handoff
  • Read or update variables on a Figma Enterprise plan to align with the design system

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Figma access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Figma API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Figma changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Figma connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Figma connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Figma account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Figma's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to Figma?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Figma account it signs in with. Revoking access is one click in Figma.

More on the Figma connector

Figma connector for claude.aiMiro + Claude CodeGitHub + Claude CodeLinear + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connectorTalk to us