Design feedback at a glance.
Your agent reads Figma files down to the layer, renders frames as images, collects open comments and checks your library's components, styles and variables.
- Coverage: nearly complete
- 38 tools · 12 of them make changes
Read and change.
Your agent works with exactly the permissions of the connected account. Read tools are quick to enable. Tools that change data stay off until you explicitly turn them on.
What your agent can read
- Files with pages, frames and layers, metadata and version history.
- Frames as PNG, JPG, SVG or PDF.
- Comments with replies and reactions.
- A team's folders and files, published components and styles.
- With Figma Enterprise: variables and how often components, styles and variables are used.
What your agent can change
- Comment, reply and react.
- Create and maintain dev resources: links to code, tickets and docs on layers.
- With Figma Enterprise, create and change variables.
- With admin access: webhooks for file updates, comments and library publishes.
Only once you enable it, per agent and per tool. If you want, a person also approves each action before it runs.
How teams use Figma.
Marketing, sales and RevOps run these as recurring routines or on request.
- 01
Collect open comments
Before the design review- Get the file's open comments
- Sort them by page and frame
- Flag contradictions and open questions
ResultOne list of everything that needs a decision instead of 40 comments going in circles.
- 02
New screens for marketing
When a feature goes live- Find the final frames
- Render them as PNG
- Hand the links to the campaign or Canva template
ResultMarketing has the current screens without asking the design team.
Built-in safeguards
- The agent only sees files the signed-in person has access to.
- Deleting comments and variables needs your approval. The activity log and webhooks are only available with admin access.
- If you want, changes only run after a person approves them, for example the team lead: in the Data Hub, in Slack or via a link. On top of that, each agent has daily and hourly limits.
- Guardrails for every agent: deletes and changes to more than 10 records need approval by default, an emergency brake kicks in on a run of deletes, and you can set your own rules per tool.
- Each connection has an access level: Read, Write or Admin. Where the vendor allows it, the Data Hub only requests the permissions for that level.
- Credentials are stored encrypted in the Data Hub, and the agent never sees them. Every call is logged.
What it can't do
- This connection can't draw on the canvas: creating or moving layers only works in Figma itself.
- The hub doesn't pass through Figma's own MCP server, because Figma only admits clients from its catalog there.
- How many requests you can make depends on plan and seat. There is no undo.
What's possible here depends on what Figma offers through its API. We make available what the API allows, as ready-made tools or through the generic API request to Figma, and we check new API versions regularly.
Connect Figma to your agents.
In 30 minutes, we'll show you the Data Hub with your own tools.