SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Moosend MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Moosend MCP. Add new subscriber to welcome list, get all campaigns sent last month, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Moosend logoMoosend
Api Key

Moosend is a cloud-based, AI-powered email marketing platform for automated campaigns. Reach your audience efficiently with personalization, analytics, and powerful segmentation.

34 Tools

Introduction

This guide walks you through connecting Moosend to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Moosend agent that can send and schedule campaigns, manage mailing lists and subscribers, build segments, clone campaigns, and check engagement reports through natural language commands.

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

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

Also integrate Moosend with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Moosend MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Moosend account. It provides structured and secure access to your email marketing platform, so your agent can perform actions like managing subscribers, automating campaigns, creating mailing lists, and customizing audience data on your behalf.

  • Subscriber management and segmentation: Add, update, or search for subscribers in your mailing lists, letting your agent keep your audience organized and up to date.
  • Campaign creation and analytics: Retrieve, inspect, and manage email campaigns—enabling your agent to help you monitor, review, or even clean up your marketing activities.
  • Mailing list automation: Create or delete mailing lists as needed, so your agent can reorganize or streamline your audience targeting at scale.
  • Custom fields and personalization: Build or remove custom fields in your lists, empowering the agent to personalize campaigns and collect richer subscriber data.
  • Campaign and list cleanup: Direct your agent to permanently remove campaigns or mailing lists you no longer need, keeping your marketing hub tidy and efficient.

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: ["moosend"],
  });

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

  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 moosend, 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 Moosend 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 Moosend action and event your agent gets out of the box.

Add Segment Criteria

Tool to add a new criterion (rule) to a segment.

Add or Update Subscriber

Tool to add or update a subscriber in a mailing list.

Bulk Subscribe

Add or update up to 1000 subscribers in one Moosend mailing-list request.

Clone Campaign

Tool to clone an existing campaign, creating an exact copy with the same content and settings.

Create custom field

Tool to create a custom field in a mailing list.

Create Mailing List

Tool to create a new empty mailing list in Moosend.

Create Segment

Tool to create a new segment for a mailing list.

Delete Campaign

Permanently deletes a campaign from your Moosend account by its ID.

Delete custom field

Tool to remove a custom field definition from a mailing list.

Delete Mailing List

Tool to delete a mailing list.

Get all campaigns

Retrieves a page of campaigns in your account.

Get All Subscribers

Retrieves all subscribers from a specified mailing list, filtered by their subscription status (Subscribed, Unsubscribed, Bounced, or Removed).

Get Campaign Details

Retrieves comprehensive details about a specific campaign by its ID.

Get Campaign Engagement Report

Return one page of recipient-level campaign open or link-click activity.

Get Campaign Stats by Location

Retrieves a detailed report of campaign opens (unique and total) by country.

Get Mailing List Details

Gets details for a given mailing list including name, member counts, status, and custom field definitions.

Get Subscriber By Email

Retrieves detailed subscriber information by email address from a specific mailing list.

List all mailing lists

Retrieves a page of mailing lists in your account, with optional statistics and sorting.

List all senders

Tool to retrieve a list of all active senders in your account.

List campaigns with paging

Tool to retrieve a paginated list of all campaigns in your account with detailed information.

List Segments

Tool to get a list of all segments with their criteria for a specified mailing list.

Remove Multiple Subscribers

Tool to permanently remove multiple subscribers from a mailing list.

Remove Subscriber

Permanently remove one subscriber without suppressing the email address.

Schedule Campaign

Request scheduling of a Moosend campaign by ID for a specified delivery date and time, with an optional time zone.

Send Campaign

Tool to send an existing draft campaign immediately.

Unschedule Campaign

Tool to unschedule a campaign.

Unsubscribe From Account

Tool to unsubscribe a subscriber from the account.

Unsubscribe from Mailing List

Tool to unsubscribe a subscriber from a specified mailing list.

Update Campaign

Tool to update a draft campaign.

Update custom field

Updates a custom field in a mailing list by list and field ID.

Update Mailing List

Tool to update the properties of an existing mailing list.

Update Segment

Tool to update properties and criteria of an existing segment.

Update Segment Criteria

Tool to update an existing criterion in a segment.

Update Subscriber

Tool to update a subscriber in the specified mailing list.

FRAMEWORKS

How to build Moosend MCP Agent with another framework

Claude Code logo

Claude Code

Use Moosend MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Moosend MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Moosend MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Moosend MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Moosend MCP with Grok Bot

Codex logo

Codex

Use Moosend MCP with Codex

OpenClaw logo

OpenClaw

Use Moosend MCP with OpenClaw

Hermes logo

Hermes

Use Moosend MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Moosend MCP with Atomic Agent

Google ADK logo

Google ADK

Use Moosend MCP with Google ADK

LangChain logo

LangChain

Use Moosend MCP with LangChain

Mastra AI logo

Mastra AI

Use Moosend MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Moosend MCP with LlamaIndex

CrewAI logo

CrewAI

Use Moosend MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Moosend MCP with Pydantic AI

AutoGen logo

AutoGen

Use Moosend MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Moosend.It takes 30 seconds.

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

Start building