# How to integrate Figma MCP with Vercel AI SDK v6

```json
{
  "title": "How to integrate Figma MCP with Vercel AI SDK v6",
  "toolkit": "Figma",
  "toolkit_slug": "figma",
  "framework": "Vercel AI SDK",
  "framework_slug": "ai-sdk",
  "url": "https://composio.dev/toolkits/figma/framework/ai-sdk",
  "markdown_url": "https://composio.dev/toolkits/figma/framework/ai-sdk.md",
  "updated_at": "2026-05-12T10:11:20.573Z"
}
```

## Introduction

This guide walks you through connecting Figma to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Figma agent that can add a comment to this figma file, convert design tokens to tailwind css, delete a reaction from a comment through natural language commands.
This guide will help you understand how to give your Vercel AI SDK agent real control over a Figma account through Composio's Figma MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Figma with

- [ChatGPT](https://composio.dev/toolkits/figma/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/figma/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/figma/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/figma/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/figma/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/figma/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/figma/framework/codex)
- [Cursor](https://composio.dev/toolkits/figma/framework/cursor)
- [VS Code](https://composio.dev/toolkits/figma/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/figma/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/figma/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/figma/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/figma/framework/cli)
- [Google ADK](https://composio.dev/toolkits/figma/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/figma/framework/langchain)
- [Mastra AI](https://composio.dev/toolkits/figma/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/figma/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/figma/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- How to set up and configure a Vercel AI SDK agent with Figma integration
- Using Composio's Tool Router to dynamically load and access Figma tools
- Creating an MCP client connection using HTTP transport
- Building an interactive CLI chat interface with conversation history management
- Handling tool calls and results within the Vercel AI SDK framework

## What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.
Key features include:
- streamText: Core function for streaming responses with real-time tool support
- MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
- Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
- OpenAI Provider: Native integration with OpenAI models

## What is the Figma MCP server, and what's possible with it?

The Figma MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Figma account. It provides structured and secure access to your Figma workspace, so your agent can perform actions like commenting on designs, managing design tokens, linking developer resources, and automating collaboration workflows on your behalf.
- Automated commenting and feedback loops: Have your agent add, reply to, or delete comments on Figma files and branches to streamline design reviews and team discussions.
- Design token management and conversion: Let the agent extract, update, or convert design tokens in your files, including generating Tailwind CSS configurations for seamless dev handoff.
- Developer resource integration: Automatically attach, update, or remove dev resources linked to Figma nodes, bridging the gap between design and development with contextual documentation or code references.
- Webhook setup and automation: Enable your agent to create or delete webhooks for team events, making it easy to trigger notifications or workflows based on design activity.
- Collaborative variable management: Empower the agent to batch-create, modify, or delete variables, collections, and modes across your design system, keeping everything consistent and up to date.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `FIGMA_ADD_A_COMMENT_TO_A_FILE` | Add a comment to a file | Posts a new comment to a Figma file or branch, optionally replying to an existing root comment (replies cannot be nested); `region_height` and `region_width` in `client_meta` must be positive if defining a comment region. |
| `FIGMA_ADD_A_REACTION_TO_A_COMMENT` | Add a reaction to a comment | Posts a specified emoji reaction to an existing comment in a Figma file or branch, requiring valid file_key and comment_id. |
| `FIGMA_CREATE_A_WEBHOOK` | Create a webhook | Creates a Figma webhook to receive POST notifications when specific events occur. Webhooks can monitor events at three scopes: - Team level: monitors all files in a team (requires team admin permissions) - Project level: monitors all files in a project (requires edit access) - File level: monitors a specific file (requires edit access) Upon creation, Figma sends an initial PING event to verify your endpoint (unless status is PAUSED). IMPORTANT: team_id, project_id, and file_key cannot be discovered programmatically. Extract them from Figma URLs or use FIGMA_DISCOVER_FIGMA_RESOURCES to parse URLs. |
| `FIGMA_CREATE_DEV_RESOURCES` | Create dev resources | Creates and attaches multiple uniquely-URLed development resources to specified Figma nodes, up to 10 per node. |
| `FIGMA_CREATE_MODIFY_DELETE_VARIABLES` | Create, modify, or delete variables | Manages variables, collections, modes, and their values in a Figma file via batch create/update/delete operations; use temporary IDs to link new related items in one request and ensure `variableModeValues` match the target variable's `resolvedType`. |
| `FIGMA_DELETE_A_COMMENT` | Delete a comment | Deletes a specific comment from a Figma file or branch, provided the authenticated user is the original author of the comment. |
| `FIGMA_DELETE_A_REACTION` | Delete a reaction | Deletes a specific emoji reaction from a comment in a Figma file; the user must have originally created the reaction. |
| `FIGMA_DELETE_A_WEBHOOK` | Delete a webhook | Permanently deletes an existing webhook, identified by its unique `webhook_id`; this operation is irreversible. |
| `FIGMA_DELETE_DEV_RESOURCE` | Delete dev resource | Deletes a development resource (used to link Figma design elements to external developer information like code or tasks) from a specified Figma file. |
| `FIGMA_DESIGN_TOKENS_TO_TAILWIND` | Design tokens to tailwind | Convert design tokens to Tailwind CSS configuration. TWO-STEP WORKFLOW: 1. First, call FIGMA_EXTRACT_DESIGN_TOKENS with a Figma file_key to extract design tokens 2. Then, pass the returned DesignTokens object to this action's 'tokens' parameter This action generates: - tailwind.config.ts/js with theme extensions - Optional globals.css with font imports Note: Shadow colors can be provided in either string format (e.g., "rgba(15, 110, 110, 0.32)") or dictionary format (e.g., {"r": 0.059, "g": 0.431, "b": 0.431, "a": 0.32}). |
| `FIGMA_DETECT_BACKGROUND` | Detect Background Layers | Detect background layers for selected nodes in a Figma file. This action analyzes the Figma document structure and identifies potential background elements for the given target nodes. It uses: - Geometric analysis (bounding box overlap/containment) - Z-index ordering (nodes earlier in the layer stack are behind later ones) - Visual properties (fills, node types) - Naming conventions (nodes named 'background', 'bg', etc.) Returns background candidates with confidence scores (0-1) and explanations. |
| `FIGMA_DISCOVER_FIGMA_RESOURCES` | Discover Figma Resources | Smart Figma resource discovery - extract IDs from any Figma URL. Supports all URL formats: /file/, /design/, /board/, /proto/, /slides/ Example: figma.com/board/ABC123/Name → file_key=ABC123 Discovery workflow: team_id → projects → files → nodes Use extracted IDs with GetFileJson, DetectBackground, etc. |
| `FIGMA_DOWNLOAD_FIGMA_IMAGES` | Download Figma Images | Download images from Figma file nodes. Renders specified nodes as images and downloads them. Supports PNG, SVG, JPG, and PDF formats. REQUIRED PARAMETERS: - file_key (string): The Figma file key from the URL - images (array): List of objects, each containing: - node_id (string, required): The node ID to export (e.g., "1:2") - file_name (string, required): Output filename with extension (e.g., "logo.png") - format (string, optional): One of 'png', 'svg', 'jpg', 'pdf'. Defaults to 'png' Example usage: { "file_key": "abc123XYZ", "images": [ {"node_id": "1:2", "file_name": "logo.png", "format": "png"} ] } To find node IDs, use FIGMA_GET_FILE_JSON or look in Figma URLs after 'node-id='. NOTE: Returned image URLs expire shortly after generation — download them immediately. |
| `FIGMA_EXTRACT_DESIGN_TOKENS` | Extract design tokens | Extract design tokens from Figma files by combining styles, variables, and node-extracted values. Only values defined as Figma styles or variables are captured — any design values not encoded as styles/variables are silently omitted. Requires `file_variables:read` scope and a Figma plan that supports variables for full output; if variables return empty, supplement with FIGMA_GET_LOCAL_VARIABLES. |
| `FIGMA_EXTRACT_PROTOTYPE_INTERACTIONS` | Extract Prototype Interactions | Extract prototype interactions and animations from Figma files. Required parameter: - file_key: The Figma file key extracted from a URL like 'https://www.figma.com/file/ABC123xyz/MyFile' (the 'ABC123xyz' part) Analyzes the prototype data to extract: - User interactions (clicks, hovers, etc.) - Transition animations - Component variant states - User flows and navigation |
| `FIGMA_GET_ACTIVITY_LOGS` | Get activity logs | Retrieves activity log events from Figma, allowing filtering by event types, time range, and pagination. |
| `FIGMA_GET_A_WEBHOOK` | Get a webhook | Retrieves detailed information about a specific webhook by its ID, provided the webhook exists and is accessible to the user. |
| `FIGMA_GET_COMMENTS_IN_A_FILE` | Get comments in a file | Retrieves all comments from an existing Figma file, identified by a valid `file_key`, returning details like content, author, position, and reactions, with an option for Markdown formatted content. |
| `FIGMA_GET_COMPONENT2` | Get component | Fetches metadata for a specific component using its unique identifier. Use when you need to retrieve published component details from a team library. |
| `FIGMA_GET_COMPONENT_SET` | Get component set | Retrieves detailed metadata for a specific published Figma component set using its unique `key`. |
| `FIGMA_GET_CURRENT_USER` | Get current user | Retrieves detailed information for the currently authenticated Figma user. |
| `FIGMA_GET_DEV_RESOURCES` | Get dev resources | Retrieves development resources (e.g., Jira/GitHub links) for a Figma main file, optionally filtering by specific node IDs. |
| `FIGMA_GET_FILE_COMPONENTS` | Get file components | Retrieves published components from a Figma file, which must be a main file (not a branch) acting as a library. |
| `FIGMA_GET_FILE_COMPONENT_SETS` | Get file component sets | Retrieves all published component sets from the specified Figma main file (file_key must not be for a branch). |
| `FIGMA_GET_FILE_JSON` | Get file json | Get Figma Design file data with automatic simplification. IMPORTANT: Only supports Design files (figma.com/design/{file_key}). FigJam board files (figma.com/board/{file_key}) and Slides files (figma.com/slides/{file_key}) are NOT supported and will return a 400 error: "File type not supported by this endpoint". This enhanced version automatically transforms verbose Figma JSON into clean, AI-friendly format with: - CSS-like property names - Deduplicated variables - Removed empty values - 70%+ size reduction Use simplify=False to get raw API response. |
| `FIGMA_GET_FILE_METADATA` | Get file metadata | Get Figma file metadata including name, creator, last modification details, thumbnail, and access information. Use when you need quick file overview without the full document tree. |
| `FIGMA_GET_FILE_NODES` | Get file nodes | Fetch JSON for specific node IDs from a Figma file to avoid full-file payload limits. Use when you already know target node IDs (from shallow file fetch or component listings) or when full-file JSON has hit payload limits. Prefer depth=1 for fast discovery. |
| `FIGMA_GET_FILES_IN_A_PROJECT` | Get files in a project | Fetches a list of files in a Figma project, optionally including branch metadata. |
| `FIGMA_GET_FILE_STYLES` | Get file styles | Retrieves a list of published styles (like colors, text attributes, effects, and layout grids) from a specified main Figma file (not a branch). |
| `FIGMA_GET_IMAGE_FILLS` | Get image fills | Retrieves temporary (14-day expiry) download URLs for all image fills in a Figma file; requires `imageRef` from `Paint` objects to map URLs. |
| `FIGMA_GET_LIBRARY_ANALYTICS_COMPONENT_ACTION_DATA` | Get library analytics component action data | Retrieves component insertion and detachment analytics for a specified Figma library, groupable by 'component' or 'team' and filterable by a date range (YYYY-MM-DD). |
| `FIGMA_GET_LIBRARY_ANALYTICS_COMPONENT_USAGE_DATA` | Get library analytics component usage data | Retrieves component usage analytics for a specified Figma library file (identified by `file_key`), with data groupable by 'component' or 'file'. |
| `FIGMA_GET_LIBRARY_ANALYTICS_STYLE_ACTION_DATA` | Get library analytics style action data | Retrieves style usage analytics (insertions, detachments) for a Figma library, grouped by 'style' or 'team'; if providing a date range, ensure end_date is not before start_date. |
| `FIGMA_GET_LIBRARY_ANALYTICS_STYLE_USAGE_DATA` | Get library analytics style usage data | Retrieves style usage analytics for a published Figma library. Returns data about how styles (colors, text styles, effects, grids) from the library are being used across your organization. Requires Enterprise plan and library_analytics:read scope. Group results by 'style' to see per-style metrics or by 'file' to see which files use the library's styles. |
| `FIGMA_GET_LIBRARY_ANALYTICS_VARIABLE_ACTION_DATA` | Get library analytics variable action data | Retrieves weekly, paginated analytics data on variable insertions and detachments for a specified Figma library (identified by `file_key`), groupable by 'variable' or 'team', and filterable by an optional date range. Note: Requires Enterprise plan and library_analytics:read scope. |
| `FIGMA_GET_LIBRARY_ANALYTICS_VARIABLE_USAGE_DATA` | Get library analytics variable usage data | Retrieves paginated analytics data on variable usage from a specified Figma library, grouped by 'file' or 'variable', for libraries with enabled analytics. |
| `FIGMA_GET_LOCAL_VARIABLES` | Get local variables | Retrieves all local/remote variables for a Figma file/branch; crucial for obtaining mode-specific values which `/v1/files/{file_key}/variables/published` omits. |
| `FIGMA_GET_PAYMENTS` | Get payments | Retrieves a user's payment information for a Figma plugin, widget, or Community file; the authenticated identity must own the resource. |
| `FIGMA_GET_PROJECTS_IN_A_TEAM` | Get projects in a team | Retrieves projects within a specified Figma team that are visible to the authenticated user. |
| `FIGMA_GET_PUBLISHED_VARIABLES` | Get published variables | Retrieves variables published from a specified Figma file; this API is available only to full members of Enterprise organizations. |
| `FIGMA_GET_REACTIONS_FOR_A_COMMENT` | Get reactions for a comment | Retrieves reactions for a specific comment in a Figma file. |
| `FIGMA_GET_SCIM_SERVICE_PROVIDER_CONFIG` | Get SCIM service provider config | Get Figma's SCIM service provider configuration. Returns configuration details including which SCIM operations are supported (patch, bulk, filter, etc.), authentication schemes, and service capabilities. |
| `FIGMA_GET_STYLE` | Get style | Retrieves detailed metadata for a specific style in Figma using its unique style key. |
| `FIGMA_GET_TEAM_COMPONENTS` | Get team components | Retrieves components published in a specific Figma team's library; the team must have published components, otherwise an empty list is returned. |
| `FIGMA_GET_TEAM_COMPONENT_SETS` | Get team component sets | Retrieves a paginated list of published component sets (collections of reusable UI elements) from a specified Figma team's library. |
| `FIGMA_GET_TEAM_STYLES` | Get team styles | Retrieves a paginated list of published styles (fill colors, text styles, effects, grids) from a specified Figma team's library. Note: The team must have published styles in its library for this endpoint to return data. Teams without published styles will return an empty list. |
| `FIGMA_GET_TEAM_WEBHOOKS` | Get webhooks | Retrieves all webhooks registered for a specified Figma context (team, project, or file). Uses the Figma Webhooks V2 API endpoint (GET /v2/webhooks) with context and context_id query parameters. This is the recommended approach as the legacy path-based endpoint (/v2/teams/{team_id}/webhooks) is deprecated. Note: team_id, project_id, and file_key cannot be discovered programmatically via the API. Extract them from Figma URLs or use FIGMA_DISCOVER_FIGMA_RESOURCES to parse URLs. |
| `FIGMA_GET_VERSIONS_OF_A_FILE` | Get versions of a file | Retrieves the version history for a Figma file or branch, as specified by its `file_key`. |
| `FIGMA_GET_WEBHOOK_REQUESTS` | Get webhook requests | Retrieves a history of webhook requests for a specific Figma webhook subscription; data is available for requests sent within the last seven days. |
| `FIGMA_RENDER_IMAGES_OF_FILE_NODES` | Render images of file nodes | Render Figma nodes as images (PNG, JPG, SVG, PDF). Returns a map of node IDs to temporary image URLs (valid for 30 days). Images are capped at 32 megapixels; larger requests are automatically scaled down. REQUIRED PARAMETERS: - file_key: Figma file key from URL (e.g., 'abc123XYZ' from figma.com/design/abc123XYZ/...) - ids: Comma-separated node IDs to render (e.g., '1:2' or '1:2,1:3,1:4') NODE IDs: Found in Figma URLs after 'node-id=' or from FIGMA_GET_FILE_JSON response. FORMATS: - png/jpg: Raster images with optional scale (0.01-4.0) - svg: Vector graphics with text outline options - pdf: Document format COMMON ISSUES: - null value in images map = node failed to render (invalid ID, invisible, 0% opacity) - 404 error = file_key not found or no access - 429 error = rate limit exceeded, wait and retry |
| `FIGMA_UPDATE_A_WEBHOOK` | Update a webhook | Updates an existing Figma webhook, identified by `webhook_id`, allowing modification of its event type, endpoint, passcode, status, or description. |
| `FIGMA_UPDATE_DEV_RESOURCES` | Update dev resources | Updates the name and/or URL of one or more existing Figma Dev Resources, each identified by its unique `id`. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Figma MCP server is an implementation of the Model Context Protocol that connects your AI agent to Figma. It provides structured and secure access so your agent can perform Figma operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Node.js and npm installed
- A Composio account with API key
- An OpenAI API key

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) and create an API key. You'll need credits to use the models, or you can connect to another model provider.
- Keep the API key safe.
Composio API Key
- Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install required dependencies

First, install the necessary packages for your project.
What you're installing:
- @ai-sdk/openai: Vercel AI SDK's OpenAI provider
- @ai-sdk/mcp: MCP client for Vercel AI SDK
- @composio/core: Composio SDK for tool integration
- ai: Core Vercel AI SDK
- dotenv: Environment variable management
```bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv
```

### 3. Set up environment variables

Create a .env file in your project root.
What's needed:
- OPENAI_API_KEY: Your OpenAI API key for GPT model access
- COMPOSIO_API_KEY: Your Composio API key for tool access
- COMPOSIO_USER_ID: A unique identifier for the user session
```bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
```

### 4. Import required modules and validate environment

What's happening:
- We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
- The dotenv/config import automatically loads environment variables
- The MCP client import enables connection to Composio's tool server
```typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
```

### 5. Create Tool Router session and initialize MCP client

What's happening:
- We're creating a Tool Router session that gives your agent access to Figma tools
- The create method takes the user ID and specifies which toolkits should be available
- The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
- This session provides access to all Figma-related tools through the MCP protocol
```typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["figma"],
  });

  const mcpUrl = session.mcp.url;
```

### 6. Connect to MCP server and retrieve tools

What's happening:
- We're creating an MCP client that connects to our Composio Tool Router session via HTTP
- The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
- The type: "http" is important - Composio requires HTTP transport
- tools() retrieves all available Figma tools that the agent can use
```typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
```

### 7. Initialize conversation and CLI interface

What's happening:
- We initialize an empty messages array to maintain conversation history
- A readline interface is created to accept user input from the command line
- Instructions are displayed to guide the user on how to interact with the agent
```typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to figma, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
```

### 8. Handle user input and stream responses with real-time tool feedback

What's happening:
- We use streamText instead of generateText to stream responses in real-time
- toolChoice: "auto" allows the model to decide when to use Figma tools
- stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
- onStepFinish callback displays which tools are being used in real-time
- We iterate through the text stream to create a typewriter effect as the agent responds
- The complete response is added to conversation history to maintain context
- Errors are caught and displayed with helpful retry suggestions
```typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
```

## Complete Code

```typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["figma"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to figma, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
```

## Conclusion

You've successfully built a Figma agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.
Key features of this implementation:
- Real-time streaming responses for a better user experience with typewriter effect
- Live tool execution feedback showing which tools are being used as the agent works
- Dynamic tool loading through Composio's Tool Router with secure authentication
- Multi-step tool execution with configurable step limits (up to 10 steps)
- Comprehensive error handling for robust agent execution
- Conversation history maintenance for context-aware responses
You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

## How to build Figma MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/figma/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/figma/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/figma/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/figma/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/figma/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/figma/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/figma/framework/codex)
- [Cursor](https://composio.dev/toolkits/figma/framework/cursor)
- [VS Code](https://composio.dev/toolkits/figma/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/figma/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/figma/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/figma/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/figma/framework/cli)
- [Google ADK](https://composio.dev/toolkits/figma/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/figma/framework/langchain)
- [Mastra AI](https://composio.dev/toolkits/figma/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/figma/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/figma/framework/crew-ai)

## Related Toolkits

- [Abyssale](https://composio.dev/toolkits/abyssale) - Abyssale is a creative automation platform for generating images, videos, GIFs, PDFs, and HTML5 content programmatically. It streamlines and scales visual content production for marketing, design, and operations teams.
- [Alttext ai](https://composio.dev/toolkits/alttext_ai) - AltText.ai is a service that generates alt text for images automatically. It helps boost accessibility and SEO for your visual content.
- [Bannerbear](https://composio.dev/toolkits/bannerbear) - Bannerbear is an API-driven platform for generating images and videos automatically at scale. It helps businesses create custom graphics, social visuals, and marketing assets using powerful templates.
- [Canva](https://composio.dev/toolkits/canva) - Canva is a drag-and-drop design suite for creating professional graphics, presentations, and marketing materials. It makes it easy for anyone to design with beautiful templates and a vast library of elements.
- [Claid ai](https://composio.dev/toolkits/claid_ai) - Claid.ai delivers AI-driven image editing APIs for tasks like background removal, upscaling, and color correction. It helps automate and enhance image workflows with powerful, developer-friendly tools.
- [Cloudinary](https://composio.dev/toolkits/cloudinary) - Cloudinary is a cloud-based platform for managing, uploading, and transforming images and videos. It streamlines media workflows and delivers optimized assets globally.
- [Cults](https://composio.dev/toolkits/cults) - Cults is a digital marketplace for 3D printing models, connecting designers and makers. It lets creators share, sell, and discover a huge variety of printable designs easily.
- [DeepImage](https://composio.dev/toolkits/deepimage) - DeepImage is an AI-powered image enhancer and upscaler. Get higher-quality images with just a few clicks.
- [Dreamstudio](https://composio.dev/toolkits/dreamstudio) - DreamStudio is Stability AI’s platform for generating and editing images with AI. It lets you easily turn ideas into stunning visuals, fast.
- [Dynapictures](https://composio.dev/toolkits/dynapictures) - Dynapictures is a cloud-based platform for generating personalized images at scale. Instantly create hundreds of custom visuals using your data sources, like Google Sheets.
- [Fal.ai](https://composio.dev/toolkits/fal_ai) - Fal.ai is a generative media platform offering 600+ AI models for images, video, voice, and audio. Developers use Fal.ai for fast, scalable access to cutting-edge generative AI tools.
- [Gamma](https://composio.dev/toolkits/gamma) - Gamma is an AI-powered platform for making beautiful, interactive presentations and documents. It lets anyone create and share engaging decks with minimal effort.
- [Html to image](https://composio.dev/toolkits/html_to_image) - Html to image converts HTML and CSS into images or captures web page screenshots. Instantly generate visuals from code or web content—no manual screenshots needed.
- [Imagior](https://composio.dev/toolkits/imagior) - Imagior is an AI-powered image generation platform that lets you create and customize images using dynamic templates and APIs. Perfect for businesses and creators needing fast, scalable visuals without design hassle.
- [Imejis io](https://composio.dev/toolkits/imejis_io) - Imejis io is an API-based image generation platform with powerful customization and template support. It lets you create and modify images in seconds, no manual design work required.
- [Imgix](https://composio.dev/toolkits/imgix) - Imgix is a real-time image processing and delivery service for developers. It helps you optimize, transform, and deliver images efficiently at any scale.
- [Kraken io](https://composio.dev/toolkits/kraken_io) - Kraken.io is an image optimization and compression platform. It helps you shrink image file sizes while keeping visual quality intact.
- [Logo dev](https://composio.dev/toolkits/logo_dev) - Logo.dev is an API and database for high-resolution company logos and brand metadata. Instantly fetch official logos from any domain without scraping or manual searching.
- [Miro](https://composio.dev/toolkits/miro) - Miro is a collaborative online whiteboard platform for teams to brainstorm, design, and manage projects visually. It streamlines teamwork by enabling real-time idea sharing, diagramming, and workflow planning in a single space.
- [Mural](https://composio.dev/toolkits/mural) - Mural is a digital whiteboard platform for distributed visual collaboration. It helps teams brainstorm, map ideas, and diagram together in real time.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Figma MCP?

With a standalone Figma MCP server, the agents and LLMs can only access a fixed set of Figma tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Figma and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Figma tools.

### Can I manage the permissions and scopes for Figma while using Tool Router?

Yes, absolutely. You can configure which Figma scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Figma data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)