SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Brevo MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Brevo MCP. Send sms campaign to new subscribers, create or update an email template, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Brevo logoBrevo
Api KeyOauth2

Brevo is an all-in-one email and SMS marketing platform for transactional messaging, automation, and CRM. It helps businesses engage customers and streamline communications through powerful campaign tools.

62 Tools

Introduction

This guide walks you through connecting Brevo to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Brevo agent that can send transactional emails, create and send email and SMS campaigns, manage contacts and lists, and track deals through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Brevo with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKMuseCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Brevo MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Brevo account. It provides structured and secure access to your contacts, campaigns, templates, transactional email activity, SMS campaigns, and CRM records, so your agent can manage contacts, create campaigns, send emails, review messaging activity, and maintain company records on your behalf.

  • Contact and audience management: Have your agent create, update, delete, import, and review contacts, organize them into lists, and inspect configured contact attributes.
  • Email campaign creation and delivery: Direct your agent to create or update email campaigns, review campaign details, and send completed draft campaigns to their recipients.
  • Transactional email and templates: Let the agent create or update email templates, send or schedule transactional emails, and review transactional email events.
  • SMS campaign management: Instruct your agent to create SMS campaigns, review existing campaigns and their details, or delete campaigns that are no longer needed.
  • CRM and performance insights: Have your agent create, review, list, or delete companies, check contact campaign statistics, and inspect sender domains and their verification status.

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: ["brevo"],
  });

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

  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 brevo, 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 Brevo 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 Brevo action and event your agent gets out of the box.

Add Contacts to List

Add existing Brevo contacts to one list using one identifier family.

Create a company

Creates a new company record in your Brevo CRM.

Create Contact

Create a Brevo contact, or update a matching contact when explicitly enabled.

Create Contact Attribute

Create a Brevo contact attribute definition.

Create Contact List

Creates a new contact list (audience) in Brevo within a specified folder.

Create Deal

Create a Brevo CRM deal with optional attributes and associations.

Create Email Campaign

Create an email campaign as a draft, or schedule it when requested.

Create or Update Email Template

This tool creates a new email template or updates an existing one in Brevo.

Create Sender

Create a Brevo email sender identity and return DNS configuration warnings.

Create Sender Domain

Register a Brevo sender domain and return available DNS authentication records.

Create SMS Campaign

This tool allows you to create a new SMS campaign in Brevo.

Delete a company

Deletes a company from Brevo using its unique identifier.

Delete Contact

Deletes a contact from Brevo by email, contact ID, external ID, phone number, WhatsApp ID, or landline number.

Delete Contact List

Permanently delete a Brevo contact list without deleting its contacts.

Delete Email Campaign

Delete an unscheduled campaign and related template, builder, and schedule data.

Delete Email Template

This tool deletes an inactive email template from Brevo.

Delete SMS Campaign

This tool deletes an existing SMS campaign.

Export Email Campaign Recipients

Start an asynchronous CSV export of a sent email campaign's recipients.

Get Account Information

Retrieves comprehensive information about the authenticated Brevo account.

Get Aggregated Transactional Email Report

Return aggregate delivery and engagement totals for transactional emails.

Get all contacts

Retrieves a page of Brevo contacts, with filters for creation or modification dates, list IDs, or a segment ID.

Get all email templates

This tool retrieves a list of all email templates created in your Brevo account.

Get All Senders

This tool retrieves a list of all senders associated with the Brevo account.

Get Company Details

Retrieves detailed information about a specific company from Brevo's CRM.

Get Contact Campaign Stats

Retrieve a contact's email campaign statistics for a bounded date range.

Get Contact Details

This tool retrieves detailed information about a specific contact in Brevo.

Get Contact List

Get contact-list metadata and optional campaign statistics by list ID.

Get contact lists

Retrieve one page of Brevo contact lists, including list IDs and names and, when returned, subscriber counts and folder associations.

Get Email Campaign Details

Retrieve details for a specific email campaign, including available HTML content, recipients, and statistics.

Get Email Template

Retrieve one transactional email template by numeric or custom ID.

Get Process

Retrieve the status and available result details of a Brevo process.

Get SMS Campaign Details

Retrieves the details of a specific SMS campaign.

Get SMS Campaigns

List a page of Brevo SMS campaigns, with optional status and sent-date filtering, pagination, and creation-date sorting.

Get Transactional Email

Retrieve a sent transactional email by its identifier, including event history and personalized content when retained by Brevo.

Import Contacts

Submit a contact import to Brevo and return its background process ID.

List All Companies

This action retrieves a list of all companies stored in the Brevo CRM.

List Contact Attributes

List the contact attributes configured in the Brevo account.

List Contact Folders

List folders that organize contact lists in the connected Brevo account.

List Contact Lists in Folder

List one bounded page of contact lists belonging to a Brevo folder.

List Contact Segments

List one page of contact segments configured in the Brevo account.

List CRM Notes

List one page of Brevo CRM notes, optionally filtered by entity and date.

List CRM Pipelines

List every Brevo CRM deal pipeline with its stages and stage settings.

List Custom Object Records

List one page of records for an Enterprise-only Brevo custom object.

List Deals

List one page of Brevo CRM deals with optional relationship filters.

List Email Campaigns

List a page of Brevo email campaigns, with filters for type, status, and dates.

List Orders

List one page of Brevo ecommerce orders.

List Organization Users

List active and pending users in the connected Brevo organization.

List Processes

List a bounded page of Brevo background processes for status monitoring.

List Sender Domains

List sender domains and their authentication and verification status.

List Transactional Email Events

List one page of transactional email events with Brevo's complete filter set.

List Transactional Emails

List a page of sent transactional email records, filtered by recipient email, template ID, or message ID.

Remove Contacts from List

Remove selected contacts, or every contact, from one Brevo list.

Send Email Campaign Now

Request immediate sending of an existing draft email campaign to its recipients.

Send Email Campaign Test

Send a campaign test to explicit recipients or the account test list.

Send Transactional Email

Send or schedule one or many transactional emails through Brevo.

Send Transactional Template Test

Send a transactional template test to recipients or the account test list.

Update Contact

Update fields and list memberships for an existing Brevo contact.

Update Contact List

Rename an existing Brevo contact list, move it to a folder, or both.

Update Deal

Update a Brevo CRM deal's fields or complete association lists.

Update Email Campaign

Updates an email campaign in Brevo using its unique identifier.

Update Email Campaign Status

Apply a documented lifecycle status operation to an email campaign.

Upload Campaign Image

Upload an image from a public URL to Brevo's campaign image gallery.

FRAMEWORKS

How to build Brevo MCP Agent with another framework

Claude Code logo

Claude Code

Use Brevo MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Brevo MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Brevo MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Brevo MCP with Claude Agent SDK

Muse logo

Muse

Use Brevo MCP with Muse

Codex logo

Codex

Use Brevo MCP with Codex

OpenClaw logo

OpenClaw

Use Brevo MCP with OpenClaw

Hermes logo

Hermes

Use Brevo MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Brevo MCP with Atomic Agent

Google ADK logo

Google ADK

Use Brevo MCP with Google ADK

LangChain logo

LangChain

Use Brevo MCP with LangChain

Mastra AI logo

Mastra AI

Use Brevo MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Brevo MCP with LlamaIndex

CrewAI logo

CrewAI

Use Brevo MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Brevo MCP with Pydantic AI

AutoGen logo

AutoGen

Use Brevo MCP with AutoGen

FAQ

Frequently asked questions

Start with Brevo.It takes 30 seconds.

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

Start building