# Figma for AI agents. Managed auth, ready-made tools.

> Read design files, export frames as images, and read and post comments in your users' Figma files.

- Page: https://www.agent200.com/tools/figma/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `figma`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-15

## Instructions for AI agents

Connector: Figma, through Agent200. In code: "figma".
What it does: Read design files, export frames as images, and read and post comments in your users' Figma files.
Page: https://www.agent200.com/tools/figma/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Figma's own page, through the authorization link Agent200 returns. Never ask a user for a Figma password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: figma_get_file, figma_get_file_nodes, figma_get_images, figma_list_comments, figma_list_projects, figma_list_project_files, figma_list_versions. Write tools: figma_create_comment. Name "figma" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/tools/figma/framework/claude/
   https://www.agent200.com/tools/figma/framework/chatgpt/
   https://www.agent200.com/tools/figma/framework/claude-code/
   https://www.agent200.com/tools/figma/framework/muse/
   https://www.agent200.com/tools/figma/framework/grok-bot/
   https://www.agent200.com/tools/figma/framework/openai-dots/
   https://www.agent200.com/tools/figma/framework/claude-duet/
   https://www.agent200.com/tools/figma/framework/hermes-agent/
   https://www.agent200.com/tools/figma/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Figma connector, your agent works with each user's own Figma files through Agent200: it reads a file's frames and layers, renders them as images, follows the comment threads and replies, and lists a team's projects and files. Every user connects their own account through managed OAuth.

Figma is a collaborative design tool where teams design interfaces, build prototypes and hand designs off to developers.

## Figma tools

- **Get a file** (`figma_get_file`, read): Read a file's pages, frames, layers and styles.
- **Get nodes** (`figma_get_file_nodes`, read): Read specific frames or layers of a file by their ids.
- **Render images** (`figma_get_images`, read): Export frames or layers as PNG, JPG, SVG or PDF.
- **List comments** (`figma_list_comments`, read): Read the comments on a file.
- **Add a comment** (`figma_create_comment`, write): Comment on a file or reply to a comment.
- **List team projects** (`figma_list_projects`, read): List the projects in a team.
- **List project files** (`figma_list_project_files`, read): List the files in a project.
- **Get version history** (`figma_list_versions`, read): List a file's saved versions.

## Limits you can set

**Turn single tools on or off.** Let your agent read files and comments, and switch off `figma_create_comment` if it should never post in a file.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Figma

Each end user authorizes their own Figma account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Figma account, once.
const connection = await agent200
  .user("user_123")
  .connect("figma");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Figma tools

Name the user, the model and the tools. The model decides which Figma tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "List the open comments on the checkout redesign",
    tools: ["figma"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Figma's own page. You never see or store their Figma password.

**What access is requested.** Figma lists the scopes on its consent screen, such as reading file content and reading or writing comments. The agent opens only the files that user can already open.

## Example requests

- "List the open comments on the checkout redesign"
- "Export the onboarding screens as PNG"
- "What changed in the design system file since last week"
- "Reply to Dana's comment that the spacing is fixed"

## Guides: Figma with your AI framework

- [Figma + Claude](https://www.agent200.com/tools/figma/framework/claude.md): Connect Figma to Claude through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Figma + ChatGPT](https://www.agent200.com/tools/figma/framework/chatgpt.md): ChatGPT cannot send an API key to a custom MCP server, so this guide builds Figma into your own agent with OpenAI's models and the Agent200 SDK.
- [Figma + Claude Code](https://www.agent200.com/tools/figma/framework/claude-code.md): Have Claude Code build a Figma agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.
- [Figma + Muse](https://www.agent200.com/tools/figma/framework/muse.md): Connect Figma to Muse through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Figma + Grok Bot](https://www.agent200.com/tools/figma/framework/grok-bot.md): Connect Figma to Grok Bot through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Figma + OpenAI Dots](https://www.agent200.com/tools/figma/framework/openai-dots.md): Dots cannot send an API key to a custom MCP server, so this guide builds an always-on Figma agent with OpenAI's models and the Agent200 SDK.
- [Figma + Claude Duet](https://www.agent200.com/tools/figma/framework/claude-duet.md): Connect Figma to Claude Duet through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Figma + Hermes Agent](https://www.agent200.com/tools/figma/framework/hermes-agent.md): Connect Figma to Hermes Agent through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Figma + OpenClaw](https://www.agent200.com/tools/figma/framework/openclaw.md): Connect Figma to OpenClaw through Agent200's MCP server: managed OAuth, ready-made tools and one API key.

## FAQ

### Who handles the Figma OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Figma.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Figma connection, never another user's. It cannot reach anything the user or Figma has not authorized.

### Can I limit what my agent can do in Figma?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [GitHub](https://www.agent200.com/tools/github.md): Read repositories and work with issues and pull requests as the connected user.
- [GitLab](https://www.agent200.com/tools/gitlab.md): Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.
- [Bitbucket](https://www.agent200.com/tools/bitbucket.md): List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.
- [Jira](https://www.agent200.com/tools/jira.md): Search, create and transition Jira issues for the connected user.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
