How to integrate JoggAI MCP with Vercel AI SDK v6

This guide walks you through connecting JoggAI to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working JoggAI agent that can generate your scripts, animate avatars, create product videos, sync lips to audio, and manage webhooks through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a JoggAI account through Composio's JoggAI MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
JoggAI logoJoggAI
Api Key

JoggAI is an AI video creation platform for avatar, product, lip-sync, template, and translated videos. It helps teams turn scripts, products, and media assets into polished videos through APIs.

36 Tools

Introduction

This guide walks you through connecting JoggAI to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working JoggAI agent that can generate your scripts, animate avatars, create product videos, sync lips to audio, and manage webhooks through natural language commands.

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

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

Also integrate JoggAI with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

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

The JoggAI MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your JoggAI account. It provides structured and secure access to your avatars, products, videos, templates, scripts, and supporting media assets, so your agent can create videos, generate avatars, translate content, track production tasks, and manage webhooks on your behalf.

  • Avatar and lip-sync video creation: Have your agent create talking-avatar and lip-sync videos, generate photo or product avatars, and animate selected avatar images with speech and motion.
  • Product video production: Let the agent create or update product details, generate scripts and visual previews, then render selected concepts into finished product videos.
  • Template-based video rendering: Direct your agent to produce videos from JoggAI templates using text, scripts, images, videos, avatars, voices, captions, and music.
  • Video translation and dubbing: Instruct your agent to find supported languages and translate videos with options for dubbing, lip sync, subtitles, audio-only output, and adjusted duration.
  • Media tracking and notifications: Have your agent check video and avatar generation progress, browse available voices, music, templates, and visual styles, review account credits, and manage webhook notifications.

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: ["jogg_ai"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to JoggAI 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 JoggAI-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 JoggAI 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 jogg_ai, 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 JoggAI 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 JoggAI 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: ["jogg_ai"],
  });

  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 jogg_ai, 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 JoggAI 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 JoggAI action and event your agent gets out of the box.

Animate Photo Avatar

Create a reusable animated avatar from a photo-avatar image.

Animate Product Avatar

Add motion and a voice to a selected JoggAI product-avatar image generation.

Create Asset Upload URL

Create a signed URL for uploading an asset to JoggAI.

Create Lip Sync Video

Start an asynchronous lip-sync video from publicly reachable video and audio URLs.

Create Product

Create product information from exactly one source: a product page URL, or manually supplied product details.

Create Product Video

Start a product video using a saved product and nested video, avatar, voice, audio, and script settings.

Create Product Video Previews

Generate product-video previews for one or more visual styles.

Create Talking Avatar Video

Start a talking-avatar video using an avatar and either a text script or hosted audio.

Create Template Video

Start rendering a JoggAI v2 template with typed text, script, image, or video variables and optional avatar, voice, captions, and music settings.

Create Webhook

Create a JoggAI webhook endpoint with a callback URL, delivery status, and event subscriptions.

Delete Webhook

Permanently delete one JoggAI webhook endpoint.

Generate AI Scripts

Start asynchronous AI script generation from a saved product or inline product details.

Generate Photo Avatar Image

Start AI photo-avatar image generation using JoggAI's exact demographic, style, model, and aspect-ratio modes.

Generate Product Avatar Images

Start asynchronous generation of one to four product-avatar images from a public product image and an existing avatar, reference image, or description.

Get Account and Credit Balance

Return the connected JoggAI user and remaining credit balance.

Get AI Script Task

Check an AI script generation task and return generated scripts when completed.

Get Lip Sync Video

Check a lip-sync task and return its output URLs and duration when successful.

Get Photo Avatar

Check photo-avatar motion generation and return the reusable avatar details when complete.

Get Photo Avatar Image

Check photo-avatar image generation and return the generated image URLs and keys when ready.

Get Product Avatar

Check product-avatar motion generation and return the reusable avatar when complete.

Get Product Avatar Image Task

Check a product-avatar image generation batch and return its status summary and generated image candidates.

Get Product Video

Check one product video and return its generated media when available.

Get Talking Avatar Video

Check a talking-avatar video and return its media URLs when completed.

Get Template Video

Check a template-rendered video and return its output details when complete.

Get Video Translation

Check a video translation and return translated media when complete.

List Avatars

List public, instant, photo, or product avatars available for JoggAI video generation.

List Creation Assets

Browse one music, template, visual-style, or voice catalog used to create JoggAI media.

List Product Previews

List generated JoggAI product-video previews and their statuses one page at a time.

List Product Videos

List product videos with status and sort filters, one bounded page at a time.

List Translation Languages

Return currently supported lowercase target-language identifiers for JoggAI video translation.

List Webhook Events

Return event identifiers that can be subscribed to by a JoggAI webhook.

List Webhooks

List webhook endpoints registered on the connected JoggAI account.

Render Product Video Preview

Render one selected product preview into a final video.

Translate Video

Start asynchronous video translation with optional audio-only translation, dubbing, lip sync, subtitles, and dynamic duration.

Update Product

Update an existing JoggAI product's descriptive fields.

Update Webhook

Fully replace an existing JoggAI webhook's callback URL, delivery status, and event subscriptions.

FRAMEWORKS

How to build JoggAI MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use JoggAI MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use JoggAI MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use JoggAI MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use JoggAI MCP with Claude Cowork

Codex logo

Codex

Use JoggAI MCP with Codex

OpenClaw logo

OpenClaw

Use JoggAI MCP with OpenClaw

Hermes logo

Hermes

Use JoggAI MCP with Hermes

CLI logo

CLI

Use JoggAI MCP with CLI

Google ADK logo

Google ADK

Use JoggAI MCP with Google ADK

LangChain logo

LangChain

Use JoggAI MCP with LangChain

Mastra AI logo

Mastra AI

Use JoggAI MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use JoggAI MCP with LlamaIndex

CrewAI logo

CrewAI

Use JoggAI MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with JoggAI.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies