How to integrate Esputnik 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

Esputnik logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Esputnik to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Esputnik agent that can bulk add 500 new email contacts, delete sms message template with id 123, get status of yesterday's contact import through natural language commands.

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

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

Also integrate Esputnik with

TL;DR

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

The Esputnik MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Esputnik account. It provides structured and secure access to your marketing automation tools, so your agent can perform actions like sending broadcasts, managing contacts, importing data, and handling push notifications on your behalf.

  • Bulk contact import and management: Quickly add or update thousands of contacts at once, check import status, and keep your lists up to date with minimal effort.
  • Broadcast and message control: Retrieve, review, and manage your marketing broadcasts and app inbox messages, ensuring your campaigns run smoothly.
  • Order and transactional data automation: Import and synchronize large batches of order data, keeping your marketing segmentation and triggers accurate and relevant.
  • Push and SMS notification management: Activate or deactivate push tokens, delete outdated SMS templates, and fine-tune your notification workflows directly through your agent.
  • Domain and integration setup: Register domains for web tracking or widgets, helping you expand and customize your communication reach seamlessly.

Supported Tools & Triggers

Tools
Add ContactTool to create or update a single contact in eSputnik in real-time.
Add DomainRegister a domain with eSputnik for web tracking, widgets, or web push notifications.
Add Orders BulkTool to transfer orders in bulk to eSputnik.
Add Unsubscribed EmailsTool to add email addresses to the list of unsubscribed contacts.
Add Web Push DomainTool to add a domain for web push notifications in eSputnik.
Attach Contacts to SegmentTool to attach contacts to a static segment (group) by contact IDs or external customer IDs.
Bulk Add or Update ContactsBulk add or update up to 3000 contacts in eSputnik asynchronously.
Change Mobile Push Token ActivityActivate or deactivate a mobile push notification token in eSputnik.
Create API TokenGenerate a new API token for authentication.
Create App Inbox MessageTool to create a basic App Inbox message in eSputnik.
Create Contacts from FileImport or update contacts from an external file in eSputnik.
Create Email MessageTool to create or update an email message in eSputnik.
Create Mobile Push MessageTool to create a new mobile push notification message in eSputnik.
Create SMS MessageTool to create a basic SMS message template in eSputnik.
Create Telegram MessageCreate a basic Telegram bot message in eSputnik.
Delete App Inbox MessageTool to delete an App Inbox message by its ID from eSputnik.
Delete App Inbox TranslationDelete a language translation of an App Inbox message from eSputnik.
Delete BroadcastTool to cancel a scheduled broadcast campaign.
Delete ContactTool to delete a contact by its Yespo ID.
Delete Contact by External IDDelete a contact from eSputnik using their external customer ID.
Delete Email MessageDelete a basic email message by its ID from eSputnik.
Delete Email TranslationDelete a translation of a base email message from eSputnik.
Delete Mobile Push MessageDelete a base Mobile Push message by its ID from eSputnik.
Delete Mobile Push TranslationDelete a language version of a base Mobile Push message from eSputnik.
Delete OrdersTool to schedule asynchronous deletion of orders in eSputnik.
Delete SMS MessageDelete a base SMS message template by its ID from eSputnik.
Delete SMS TranslationDelete a language version of a base SMS message from eSputnik.
Delete Telegram MessageDelete a base Telegram bot message by its ID from eSputnik.
Delete Telegram TranslationDelete a language version of a Telegram bot message from eSputnik.
Detach Contacts from SegmentTool to delete contacts from a static segment by contact IDs or external customer IDs.
Generate Event V2Tool to send backend events from websites and mobile apps to eSputnik.
Generate Event V3Tool to generate events in eSputnik v3 API.
Generate Past Events V2Tool to transfer past event data from your CRM or data store to eSputnik using v2 API.
Generate Past Events V3Tool to generate past events in eSputnik v3 API.
Get Account InfoRetrieve basic eSputnik account information.
Get App Inbox MessageRetrieves an App Inbox message by its unique identifier from eSputnik.
Get BroadcastsRetrieve a paginated list of broadcast campaigns from eSputnik.
Get ContactRetrieve complete information about a contact by their ID.
Get Contact EmailsTool to retrieve email addresses of contacts by their contact IDs.
Get Contact Import StatusRetrieve the status of a contact import session in eSputnik.
Get Contact Message HistoryRetrieve a contact's message history across multiple channels from eSputnik.
Get ContactsSearch for contacts in eSputnik using various filter criteria.
Get Contact SubscriptionsRetrieve all subscription categories a contact is enrolled in.
Get Email InterfacesTool to retrieve all configured email interfaces (sender names) from eSputnik.
Get Email MessageRetrieves an email message by its unique identifier from eSputnik.
Get Email View LinkGet a link to view an email message in browser from eSputnik.
Get Message StatusRetrieve delivery status for sent messages across all channels (email, SMS, Viber, push).
Get Mobile Push MessageRetrieves a mobile push message by its unique identifier from eSputnik.
Get Organization BalanceRetrieve the current eSputnik organization balance.
Get Organization Billing HistoryRetrieve the organization's billing history from eSputnik, broken down by day and media channel.
Get Preprocessor File StatusRetrieve the status of a preprocessor file upload session.
Get Product Feeds ConfigurationTool to retrieve product feeds configuration from eSputnik.
Get Promocodes CountGet the number of available promotional codes in eSputnik.
Get Site DomainRetrieve the organization's domain configuration from eSputnik.
Get Site Tracking ScriptRetrieve the site tracking script for your eSputnik account.
Get SMS InterfacesRetrieve all SMS interfaces (alpha names) configured for the organization.
Get Subscription CategoriesRetrieve all subscription categories for the organization.
Get Telegram MessageRetrieve a Telegram bot message by its unique identifier from eSputnik.
List Promotional CodesRetrieve a list of promotional codes from eSputnik.
List Web Push DomainsRetrieve the list of domains registered for web push notifications.
Remove From UnsubscribedTool to remove email addresses from the unsubscribed contacts list in eSputnik.
Search App Inbox MessagesSearch for mobile App Inbox messages using a part of the name or a tag.
Search ContactsSearch for all contacts in a segment (group).
Search Email MessagesSearch for email messages using a part of their name or a tag.
Search Mobile Push MessagesSearch for mobile push messages using part of the name or a tag.
Search SegmentsSearch for and retrieve available segments (groups) in eSputnik.
Search SMS MessagesSearch for SMS messages using part of their names or tags in eSputnik.
Search Telegram MessagesSearch for Telegram bot messages using a part of name or a tag.
Search Viber MessagesSearch for Viber messages using part of the name or a tag.
Search WorkflowsSearch for and retrieve available workflows from eSputnik.
Send EmailSend an email message to one or more contacts via eSputnik API.
Send Prepared MessageTool to send a prepared message to one or many contacts.
Subscribe ContactTool to subscribe a contact for double opt-in implementation.
Update App Inbox MessageTool to update the base App Inbox message in eSputnik.
Update App Inbox TranslationTool to update or add a language version for an App Inbox message in eSputnik.
Update ContactTool to update contact information by contact ID.
Update Contact SubscriptionsTool to update the subscription categories a contact is enrolled in.
Update Email MessageTool to update an existing email message in eSputnik.
Update Email TranslationTool to update or add a language version for a base email message in eSputnik.
Update Interaction StatusTool to update the status of a message interaction using interaction_id.
Update Mobile Push MessageTool to update an existing mobile push notification message in eSputnik.
Update Mobile Push TranslationTool to update or add a language version for a mobile push message in eSputnik.
Update Preprocessor File By IDTool to update a preprocessor file's data by providing a new external link.
Update SMS MessageTool to update an existing base SMS message template in eSputnik.
Update SMS TranslationTool to update a language version of an SMS message in eSputnik.
Update Telegram MessageUpdate a base Telegram bot message in eSputnik.
Update Telegram TranslationUpdate a translated telegram bot message in eSputnik.
Upload Preprocessor FileTool to upload a file for the preprocessor from an external repository.
Upload Promotional CodesTool to upload promotional codes to eSputnik in bulk.

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: ["esputnik"],
  });

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

  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 esputnik, 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 Esputnik 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 Esputnik MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Esputnik MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Esputnik MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Esputnik MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Esputnik MCP with Claude Cowork

Codex logo

Codex

Use Esputnik MCP with Codex

OpenClaw logo

OpenClaw

Use Esputnik MCP with OpenClaw

Hermes logo

Hermes

Use Esputnik MCP with Hermes

CLI logo

CLI

Use Esputnik MCP with CLI

Google ADK logo

Google ADK

Use Esputnik MCP with Google ADK

LangChain logo

LangChain

Use Esputnik MCP with LangChain

Mastra AI logo

Mastra AI

Use Esputnik MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Esputnik MCP with LlamaIndex

CrewAI logo

CrewAI

Use Esputnik MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Esputnik 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 Esputnik 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↗