How to integrate Cloudinary MCP with Vercel AI SDK v6

This guide walks you through connecting Cloudinary to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Cloudinary agent that can create a new folder for event photos, delete derived assets with ids [123,456], set up upload preset with watermarking through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Cloudinary account through Composio's Cloudinary MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Cloudinary logoCloudinary
Api Key

Cloudinary is a cloud-based platform for managing, uploading, and transforming images and videos. It streamlines media workflows and delivers optimized assets globally.

108 Tools

Introduction

This guide walks you through connecting Cloudinary to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Cloudinary agent that can create a new folder for event photos, delete derived assets with ids [123,456], set up upload preset with watermarking through natural language commands.

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

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

Also integrate Cloudinary with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Cloudinary integration
  • Using Composio's Tool Router to dynamically load and access Cloudinary 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 Cloudinary MCP server, and what's possible with it?

The Cloudinary MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cloudinary account. It provides structured and secure access to your digital asset management system, so your agent can perform actions like organizing folders, creating metadata fields, managing upload presets, and handling asset deletion on your behalf.

  • Automated folder and asset organization: Easily instruct your agent to create new asset folders or remove empty ones, keeping your Cloudinary library tidy and structured.
  • Metadata management: Let your agent create custom metadata fields or delete obsolete ones, extending and refining your asset tagging and search capabilities.
  • Preset and upload mapping creation: Have your agent set up upload presets with specific options or define dynamic folder mappings, automating consistent upload processes across your assets.
  • Resource and derived asset cleanup: Direct your agent to permanently delete assets by ID or remove unnecessary derived resources, ensuring your storage stays efficient and clutter-free.
  • Datasource entry management: Ask your agent to inactivate or delete specific datasource entries from metadata fields, keeping your metadata schema accurate and up to date.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

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
4

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
5

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 { 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
6

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: ["cloudinary"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Cloudinary 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 Cloudinary-related tools through the MCP protocol
7

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 Cloudinary tools that the agent can use
8

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 cloudinary, 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
9

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 Cloudinary 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 Cloudinary 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 { 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: ["cloudinary"],
  });

  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 cloudinary, 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 Cloudinary 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.
TOOLS

Supported Tools

Every Cloudinary action and event your agent gets out of the box.

Activate Live Stream

Tool to manually activate a Cloudinary live stream.

Create Asset Relations by Asset ID

Tool to add related assets by asset ID.

Create Asset Relations by Public ID

Tool to create relations between assets by public ID.

Create Folder

Tool to create a new asset folder.

Create Image from Text

Tool to create an image from text using Cloudinary's text generation API.

Create Live Stream

Tool to create a new live stream in Cloudinary.

Create Live Stream Output

Tool to create a new live stream output configuration.

Create Metadata Field

Tool to create a new metadata field definition.

Create Metadata Rule

Tool to create a new conditional metadata rule.

Create Multi-Resource Animation

Tool to create an animated image, video, or PDF from a set of images.

Create Slideshow

Tool to create an auto-generated video slideshow from existing Cloudinary assets.

Create Streaming Profile

Tool to create a new adaptive streaming profile in your Cloudinary account.

Create Transformation

Tool to create a new named transformation by assigning a custom name to a set of transformation parameters.

Create Trigger

Tool to create a new webhook trigger for a specified event type.

Create Upload Mapping

Tool to create a new upload mapping folder and URL template.

Create Upload Preset

Tool to create a new upload preset.

Delete Asset Relations by Asset ID

Tool to delete asset relations by asset ID.

Delete Asset Relations by Public ID

Tool to delete asset relations by public ID.

Delete Derived Resources

Tool to delete derived assets.

Delete Metadata Field Datasource Entries

Tool to delete datasource entries for a specified metadata field.

Delete Folder

Tool to delete an empty asset folder.

Delete Live Stream

Tool to delete a live stream from Cloudinary.

Delete Live Stream Output

Tool to delete a live stream output from Cloudinary.

Delete Metadata Field

Tool to delete a metadata field by external ID.

Delete Metadata Rule

Tool to delete a conditional metadata rule by its ID.

Delete Resources by Asset ID

Tool to delete resources by asset IDs.

Delete Resources by Public ID

Tool to delete Cloudinary resources by public ID, prefix, or all resources.

Delete Resources by Tags

Tool to delete Cloudinary assets by tag.

Delete Streaming Profile

Tool to delete a custom streaming profile or revert a built-in profile to original settings.

Delete Transformation (v2)

Tool to delete a named transformation from your Cloudinary account.

Delete Trigger

Tool to delete a trigger (webhook notification).

Delete Upload Mapping

Tool to delete a folder upload mapping.

Delete Upload Preset

Tool to delete an upload preset from the account.

Destroy Asset

Tool to permanently destroy a Cloudinary asset/resource by public ID.

Destroy Asset by ID

Tool to delete an asset by its immutable asset ID.

Explicit Resource Update

Tool to update an existing asset and/or eagerly generate derived transformations using Cloudinary's Explicit API.

Explode Multi-Page Resource

Tool to create derived images from multi-page files (PDF, PSD, TIFF, animated GIF) by exploding them into separate images.

Generate Archive

Tool to create an archive (ZIP or TGZ file) containing a set of assets from your Cloudinary environment.

Get Adaptive Streaming Profiles

Tool to list adaptive streaming profiles.

Get Analysis Task Status

Tool to get the status of an analysis task.

Get product environment config details

Tool to get product environment config details.

Get Live Stream

Tool to get details of a single live stream by ID.

Get Live Stream Output

Tool to get details of a single live stream output.

Get Live Stream Outputs

Tool to get a list of live stream outputs.

Get Live Streams

Tool to get a list of live streams from Cloudinary.

Get Metadata Field By ID

Tool to get a single metadata field definition by external ID.

Get Resource by Asset ID

Get Resource by Asset ID

Get Resource by Public ID

Tool to get details of a single resource by public ID.

Get Resources by Asset Folder

Tool to list assets stored directly in a specified folder.

Get Resources by Context

Tool to retrieve assets with a specified contextual metadata key/value.

Get Resources in Moderation

Tool to retrieve assets in a moderation queue by status.

Get Root Folders

Tool to list all root folders in the product environment.

Get Streaming Profile Details

Tool to get details of a single streaming profile by name.

Get Resource Tags

Tool to list all tags used for a specified resource type.

Get Transformation

Tool to retrieve details of a specific transformation.

Get Transformations

Tool to list all transformations (named and unnamed).

List Webhook Triggers

Tool to list all webhook triggers for event types in your environment.

Get Upload Mapping Details

Tool to retrieve details of a single upload mapping by folder.

Get Upload Mappings

Tool to list all upload mappings.

Get Upload Preset

Tool to retrieve details of a single upload preset by name.

Get Usage

Tool to get product environment usage details.

Get Video Views

Tool to get video analytics views from Cloudinary.

Idle Live Stream

Tool to manually idle a Cloudinary live stream.

List Images

Tool to list image assets from Cloudinary.

List Metadata Fields

Tool to list all structured metadata fields defined in your Cloudinary product environment.

List Metadata Rules

Tool to retrieve all conditional metadata rules defined in your Cloudinary account.

List Raw Files

Tool to list raw assets from Cloudinary.

List Resources by Asset IDs

Tool to retrieve multiple resources by their asset IDs.

List Resources by External IDs

Tool to retrieve resources by their external IDs.

List Resources by Tag

Tool to list resources (assets) with a specified tag.

List Resources by Type

Tool to retrieve resources (assets) by resource type and storage type.

List Resource Types

Tool to list all available resource types in your Cloudinary product environment.

List Upload Presets

Tool to list all upload presets configured in the account.

List Video Assets

Tool to list video assets from Cloudinary.

Manage Context Metadata

Tool to add or remove contextual metadata on Cloudinary assets.

Order Metadata Field Datasource

Tool to update ordering of a metadata field datasource.

Ping Cloudinary Servers

Tool to ping Cloudinary servers.

Publish Resources

Tool to publish Cloudinary assets by public IDs, prefix, or tag.

Rename or Move Resource Public ID

Tool to rename an asset's public ID using Cloudinary's rename endpoint.

Reorder Metadata Field

Tool to change the position of a specific metadata field.

Reorder Metadata Fields

Tool to reorder all metadata fields in the product environment.

Restore Metadata Field Datasource Entries

Tool to restore previously deleted datasource entries for a metadata field.

Restore Deleted Resources

Tool to restore deleted Cloudinary resources by public IDs.

Restore Resources by Asset IDs

Tool to restore backed up assets by asset IDs.

Search Assets

Tool to search and filter assets using powerful query expressions.

Search Datasource in Metadata Field

Tool to search datasource values in a metadata field.

Search Folders

Tool to search asset folders with filtering, sorting, and pagination.

Search All Metadata Field Datasources

Tool to search across all metadata field datasources.

Visual Search Assets

Tool to find images in your asset library based on visual similarity or content.

Show Folder

Tool to list sub-folders within a specified folder.

Update Asset Metadata

Tool to populate or update metadata field values on one or more Cloudinary assets.

Update Folder

Tool to rename or move an existing asset folder.

Update Live Stream

Tool to update a live stream's configuration in Cloudinary.

Update Live Stream Output

Tool to modify an existing live stream output configuration.

Update Metadata Field

Tool to update a metadata field definition by external ID.

Update Metadata Field Datasource

Tool to update the datasource (allowed values) for a metadata field.

Update Metadata Rule

Tool to update an existing conditional metadata rule.

Update Resource by Asset ID

Tool to update asset properties by asset ID in Cloudinary.

Update Resource by Public ID

Tool to update asset properties by public ID in Cloudinary.

Update Resource Tags

Tool to add, remove, replace, or remove all tags for one or more Cloudinary assets.

Update Streaming Profile

Tool to modify an existing adaptive streaming profile's configuration.

Update Transformation (v2)

Tool to update the definition of an existing named transformation.

Update Trigger

Tool to update the callback URL of an existing webhook trigger.

Update Upload Mapping

Tool to update an existing upload mapping by changing its remote URL template.

Update Upload Preset

Tool to update an existing upload preset's configuration settings.

Upload Asset

Tool to upload media assets (images, videos, raw files) to Cloudinary.

Upload File Chunk

Tool to upload a single chunk of a large file to Cloudinary.

Upload File (Auto Detect)

Tool to upload files with automatic resource type detection.

FAQ

Frequently asked questions

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

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 Cloudinary tools.

Yes, absolutely. You can configure which Cloudinary 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.

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 Cloudinary data and credentials are handled as safely as possible.

Start with Cloudinary.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Cloudinary tool your agent needs.Free to start.

Start building