How to integrate Omnisend MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Omnisend logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Omnisend to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Omnisend agent that can add new subscribers from latest signups, update contact email preferences in bulk, list all products for upcoming campaign through natural language commands.

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

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

Also integrate Omnisend with

TL;DR

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

The Omnisend MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Omnisend account. It provides structured and secure access to your ecommerce marketing data, so your agent can manage contacts, automate batch operations, update products, and streamline campaign preparation for your store.

  • Bulk contact and product management: Effortlessly create or update large sets of contacts or products in one go, perfect for onboarding new subscribers or syncing your catalog.
  • Individual contact handling: Retrieve, update, or enrich detailed contact profiles, making it easy for your agent to personalize outreach or manage subscriptions.
  • Batch job automation and tracking: Initiate batch operations and monitor their progress, status, and results to ensure smooth processing of large datasets.
  • Product catalog maintenance: List, review, or delete products directly from your Omnisend account, keeping your store's offerings up to date for campaigns.
  • Contact segmentation and filtering: Fetch paginated and filtered contact lists, enabling targeted marketing actions and smarter audience management.

Supported Tools & Triggers

Tools
Add Cart ProductTool to add a product to a cart in Omnisend (v3 API).
Create BatchTool to create a new batch operation for multiple items.
Create CartTool to create a new shopping cart in Omnisend.
Create CategoryTool to create a new category in Omnisend.
Create OrderTool to create a new order in Omnisend v3 API.
Create or Update ContactTool to create or update a contact in Omnisend.
Create ProductTool to create a new product in the Omnisend product catalog.
Create Product CategoryTool to create a new product category in the Omnisend catalog.
Delete CartTool to delete a cart from Omnisend by its ID (v3 API).
Delete CategoryTool to remove a category from Omnisend by its ID.
Delete OrderTool to delete an order from Omnisend by its ID.
Delete ProductTool to remove a product from Omnisend by its ID.
Delete Product CategoryTool to remove a product category from Omnisend by its ID.
Get BatchesTool to retrieve a list of batch operations.
Get Batch InformationTool to retrieve information about a specific batch by ID.
Get Batch ItemTool to retrieve a specific item within a batch by batchID and itemID.
Get Batch ItemsTool to retrieve processed items of a specific batch by ID.
Get BrandTool to retrieve information about the current authenticated brand.
Get CartTool to retrieve a specific cart by ID from Omnisend v3 API.
Get CategoryTool to retrieve details of a specific category by ID.
Get ContactTool to retrieve details of a single contact by ID.
Get OrderTool to retrieve details of a specific order by ID.
Get ProductTool to retrieve details of a specific product by ID from Omnisend.
Get Product CategoryTool to retrieve a specific product category by ID.
List CampaignsTool to retrieve a paginated list of campaigns with optional filtering by status and type.
List CartsTool to retrieve a paginated list of carts with optional filtering.
List CategoriesTool to retrieve a paginated list of product categories.
List ContactsTool to retrieve a paginated list of contacts with optional filtering.
List EventsTool to retrieve all custom events created in Omnisend app.
List Product CategoriesTool to retrieve a paginated list of product categories from the Omnisend catalog.
List ProductsTool to retrieve a paginated list of products.
Remove Cart ProductTool to remove a product from a cart in Omnisend.
Replace CartTool to replace an existing cart in Omnisend using the v3 API.
Replace Cart ProductTool to replace a product in a cart using Omnisend v3 API.
Replace CategoryTool to replace a category's title by ID.
Replace OrderTool to completely replace an existing order in Omnisend.
Replace ProductTool to replace an existing product in the Omnisend catalog.
Send EventTool to send a customer event to Omnisend.
Update CartTool to partially update a cart in Omnisend (v3 API).
Update Cart ProductTool to update a product in a cart (v3 API).
Update ContactTool to update fields of an existing contact by ID.
Update Order StatusTool to partially update an order status in Omnisend (v3 API).
Update Product CategoryTool to update an existing product category title in Omnisend.

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

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 { 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: ["omnisend"],
  });

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

  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 omnisend, 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 Omnisend 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 Omnisend MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Omnisend MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Omnisend MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Omnisend MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Omnisend MCP with Claude Cowork

Codex logo

Codex

Use Omnisend MCP with Codex

OpenClaw logo

OpenClaw

Use Omnisend MCP with OpenClaw

Hermes logo

Hermes

Use Omnisend MCP with Hermes

CLI logo

CLI

Use Omnisend MCP with CLI

Google ADK logo

Google ADK

Use Omnisend MCP with Google ADK

LangChain logo

LangChain

Use Omnisend MCP with LangChain

Mastra AI logo

Mastra AI

Use Omnisend MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Omnisend MCP with LlamaIndex

CrewAI logo

CrewAI

Use Omnisend MCP with CrewAI

FAQ

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

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

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

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

Used by agents from

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

Get started for freeGet a demo↗