How to integrate Etermin MCP with Vercel AI SDK v6

This guide walks you through connecting Etermin to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Etermin agent that can add new client contact for booking, remove canceled appointment from calendar, create voucher for returning customer through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Etermin account through Composio's Etermin MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Etermin logoEtermin
Api Key

eTermin is an online appointment scheduling platform for businesses to manage bookings. It streamlines client appointments, saving time and reducing scheduling conflicts.

78 Tools

Introduction

This guide walks you through connecting Etermin to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Etermin agent that can add new client contact for booking, remove canceled appointment from calendar, create voucher for returning customer through natural language commands.

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

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

Also integrate Etermin with

TL;DR

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

The Etermin MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Etermin account. It provides structured and secure access to your appointment scheduling system, so your agent can perform actions like creating contacts, managing bookings, updating resources, and handling calendar events on your behalf.

  • Automated contact and user creation: Instantly add new clients or team members to your Etermin account, streamlining onboarding and customer management.
  • Effortless appointment and calendar management: Let your agent delete existing appointments or calendars, freeing up schedules and reducing manual work.
  • Resource and service administration: Automatically create or remove resources and services, ensuring your booking system stays current as your business evolves.
  • Voucher and webhook setup: Quickly generate new vouchers for promotions or set up webhooks for real-time event notifications and integrations.
  • Contact and service deletion: Easily remove outdated contacts or services, keeping your scheduling platform organized and clutter-free.

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: ["etermin"],
  });

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

  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 etermin, 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 Etermin 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 Etermin action and event your agent gets out of the box.

Assign Calendar Service

Tool to assign a service to a calendar in eTermin.

Create Absence

Tool to create an absence (non-working time) for a specific calendar.

Create Anchortime

Tool to create anchortimes (recurring time slots) in a calendar.

Create Anchortime by Date

Tool to create anchortimes by date.

Create Appointment

Tool to create a new appointment in eTermin.

Create Appointment via Sync

Tool to create an appointment via sync in eTermin.

Create Calendar Return Time

Tool to create a return time for a calendar.

Create Contact

Tool to create a new contact in eTermin.

Create Service

Tool to create a new service in eTermin.

Create Service Group

Tool to create a new service group in eTermin.

Create User

Tool to create a new user.

Create Usermapping

Tool to create a new usermapping in eTermin.

Create Voucher

Creates a new discount voucher in eTermin.

Create Webhook

Creates a webhook (web push notification) in eTermin to receive real-time updates about appointments.

Create Working Time

Tool to create a new working time slot in eTermin.

Create Working Times Date

Tool to create a working times date slot for a calendar.

Delete Absence

Tool to delete an absence (non-working time) from a calendar.

Delete Anchortime

Delete an anchortime from eTermin by its ID.

Delete Anchortime By Date

Delete an anchortime by date using its ID.

Delete Appointment

Delete an existing appointment by its ID.

Delete Appointment via Sync

Tool to delete appointments via the sync endpoint.

Delete Calendar

Delete a calendar from your eTermin account.

Delete Calendar Return Time

Delete a return time from a calendar.

Delete Calendar Service

Delete an assigned service from a calendar in eTermin.

Delete Contact

Delete a contact from your eTermin account by its contact ID.

Delete Resource

Delete an eTermin resource by type and ID.

Delete Service

Permanently deletes a service from your eTermin account by its ID.

Delete Service Group

Delete a service group from your eTermin account by its ID.

Delete User

Deletes an existing user from the eTermin account.

Delete Usermapping

Delete a usermapping by its ID.

Delete Voucher

Permanently deletes a voucher from eTermin by its voucher code.

Delete Webhook

Delete an existing webhook by its unique identifier.

Delete Working Times

Tool to delete working times from a calendar.

Delete Working Times Date

Tool to delete working times date entries from eTermin.

Get Absences

Tool to retrieve absences (non-working times) for a specific calendar.

Get Anchortime by Date

Tool to retrieve anchortimes by date.

Get Anchortimes

Tool to retrieve anchortime details.

Get Appointment Sync

Tool to synchronize appointments incrementally from eTermin.

Get Bookingpage Logs

Tool to retrieve bookingpage request logs from eTermin.

Get Calendar Return Time

Tool to retrieve return times for a specific calendar.

Get Calendars

Tool to retrieve calendars.

Get Calendar Service Assignments

Tool to retrieve calendar service assignments.

Get Company

Tool to retrieve company account details.

Get Contact By ID

Tool to retrieve a specific contact by ID, external ID, or email.

Get Contacts

Tool to retrieve a list of contacts.

Get Deleted Appointments

Tool to retrieve a list of deleted appointments from eTermin.

Get Message Logs

Tool to retrieve message logs from eTermin.

Get Customer Ratings

Tool to retrieve a list of customer ratings from eTermin.

Get Service By ID

Tool to retrieve a specific service from eTermin.

Get Service Calendar

Tool to retrieve calendars for a specific service ID.

Get Service Group

Tool to retrieve service group details from eTermin.

Get Services

Tool to retrieve a list of services.

Get Survey Results

Tool to retrieve survey results from eTermin.

Get Timeslots

Tool to retrieve available timeslots for a specific calendar on a given date.

Get Usermapping

Tool to retrieve usermapping information.

Get Users

Tool to retrieve a list of users.

Get Working Times

Tool to retrieve working times for a specific calendar.

Get Working Times Date

Tool to retrieve working times for a specific calendar on a specific date.

List Appointments

Tool to retrieve a filtered list of appointments from eTermin in a specified date range.

List Vouchers

Retrieve all vouchers (discount codes) from your eTermin account.

List Webhooks

Tool to retrieve webhooks.

Update Service via PUT

Tool to update a service in eTermin.

Update Absence

Tool to update an absence (non-working time) for a calendar in eTermin.

Update Anchortime

Update an existing anchortime in eTermin.

Update Anchortime By Date

Tool to update anchortimes by date in eTermin.

Update Appointment

Tool to update an existing appointment in eTermin.

Update Calendar

Update an existing calendar in eTermin.

Update Calendar Return Time

Tool to update a return time for a calendar in eTermin.

Update Contact

Tool to update an existing contact in eTermin.

Update Resource

Update an existing eTermin resource (contact, service, calendar, user, or voucher).

Update Service

Tool to update an existing service.

Update Service Group

Tool to update an existing service group in eTermin.

Update Synchronised Appointment

Tool to update a synchronised appointment in eTermin.

Update Usermapping

Update an existing usermapping in eTermin.

Update Voucher

Updates an existing voucher in eTermin.

Update Webhook

Update an existing webhook configuration in eTermin.

Update Working Times

Tool to update working times for a calendar in eTermin.

Update Working Times Date

Tool to update working times date for a calendar.

FAQ

Frequently asked questions

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

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

Start with Etermin.It takes 30 seconds.

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

Start building