How to integrate Imgix MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Imgix Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Imgix to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Imgix agent that can auto-optimize all images in this folder, overlay company logo on product photos, extract main color palette from image, add a 5px white border to image through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Imgix account through Composio's Imgix MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Imgix integration
  • Using Composio's Tool Router to dynamically load and access Imgix 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
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

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

The Imgix MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Imgix account. It provides structured and secure access to your image library, so your agent can perform actions like optimizing images, applying overlays, adjusting visual properties, and extracting color palettes on your behalf.

  • Real-time image optimization: Ask your agent to automatically compress, enhance, or format images for faster delivery and better quality using Imgix's auto optimization tools.
  • Dynamic overlays and blending: Direct the agent to blend images, text, or solid colors over your base images—perfect for watermarks, banners, or creative composites.
  • Precision image adjustments: Have your agent modify image brightness, contrast, and border settings to meet your design and branding needs instantly.
  • Extract and analyze color palettes: Let your agent pull color palettes from any image, making it easy to generate theme colors or analyze brand consistency.
  • Fine-tune overlay positioning: Control exactly where overlays appear on your images by specifying alignment and pixel-level positioning through your agent.

Supported Tools & Triggers

Tools
Imgix Auto OptimizationTool to apply automatic best-effort image optimizations.
Blend OverlayTool to overlay an image, text, or color onto a base image using imgix blending parameters.
Imgix Blend AlignTool to align the overlay relative to the base image when blending.
Blend Color Over ImageTool to blend a solid color over an image using CSS keyword or hex.
Imgix Blend X PositionTool to position the overlay horizontally on an Imgix-rendered image.
Draw Image BorderTool to draw a border around an image.
Adjust Image BrightnessTool to adjust image brightness.
IMGIX_CHTool to opt in to Client Hints.
Extract Image Color PaletteTool to specify how many colors to return when extracting a color palette.
Adjust Image ContrastTool to adjust image contrast.
IMGIX_CROPTool to control cropping alignment and behavior using Imgix's 'crop' parameter.
IMGIX_CSTool to set or strip output color space/profile on an Imgix image.
IMGIX_DLTool to force asset download.
Adjust Image DPITool to embed DPI (dots-per-inch) metadata for print output on an Imgix-rendered image.
Set Device Pixel RatioTool to set device pixel ratio for an Imgix image.
Imgix URL ExpirationTool to append an expiration parameter to an Imgix URL so it returns 404 after a given time.
IMGIX_FITTool to control how an image fits target dimensions after resizing.
IMGIX_FMTool to choose output file format for the rendered asset.
Force Aspect RatioTool to force a target aspect ratio on an Imgix image.
IMGIX_HTool to set output image height in pixels or as a ratio of the source height.
Adjust Image HighlightsTool to adjust highlight tonal mapping (−100 to 0).
IMGIX_LIST_SOURCESTool to list all Sources for an account.
Set Watermark Base URLTool to set the base URL prepended to the watermark image path.
Watermark Fit ModeTool to set how a watermark fits its target dimensions.
Imgix Mark HeightTool to set watermark height on an Imgix URL in pixels or as a ratio of the watermark source.
IMGIX_MARK_PADTool to set pixel padding between a watermark and the image edge or between tiled watermarks.
Watermark WidthTool to set watermark width.
IMGIX_MASKTool to apply a mask to an image.
IMGIX_MAX_HTool to limit output image height.
IMGIX_MAX_WTool to set the maximum output width on an Imgix URL.
IMGIX_PALETTETool to extract a color palette from an image in CSS or JSON form.
Set CSS Palette PrefixTool to set class-name prefix for CSS palette output.
Set Output QualityTool to set output quality for lossy formats.
IMGIX_RECTTool to select a source-image rectangle region in Imgix before other resizing.
Imgix RotateTool to rotate an image on Imgix.
IMGIX_ROT_TYPETool to control rotation behavior when `rot` is applied.
Text OverlayTool to render a single-line UTF-8 text overlay on an image.
IMGIX_TXT_ALIGNTool to align a text overlay on an Imgix image.
Set Text ColorTool to set text overlay color on an Imgix image.
Set Text FontTool to choose font family/style for overlay text.
Set Text Outline WidthTool to set outline width around overlay text.
Text Outline ColorTool to set outline color for text.
IMGIX_TXT_SHADTool to set text shadow strength for overlay text.
IMGIX_TXT_SIZETool to set text font size in pixels.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

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

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard 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.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

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

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

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

Import required modules and validate environment

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 { experimental_createMCPClient as 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,
});
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

Create Tool Router session and initialize MCP client

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

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Imgix 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 Imgix-related tools through the MCP protocol

Connect to MCP server and retrieve tools

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();
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 Imgix tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

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

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

rl.prompt();
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

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

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);
});
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 Imgix 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

Complete Code

Here's the complete code to get you started with Imgix and Vercel AI SDK:

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 { experimental_createMCPClient as 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: ["imgix"],
  });

  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 imgix, 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 Imgix 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 Imgix MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Imgix MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Imgix MCP with Claude Agent SDK

Google ADK

Google ADK

Use Imgix MCP with Google ADK

LangChain

LangChain

Use Imgix MCP with LangChain

Mastra AI

Mastra AI

Use Imgix MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Imgix MCP with LlamaIndex

CrewAI

CrewAI

Use Imgix MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Imgix MCP?

With a standalone Imgix MCP server, the agents and LLMs can only access a fixed set of Imgix tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Imgix 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?

Yes, you can. Vercel AI SDK 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 Imgix tools.

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

Yes, absolutely. You can configure which Imgix 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 Imgix data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free