SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Botstar MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Botstar MCP. Open live chat widget for new visitor, update user profile in current chat session, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Botstar logoBotstar
Api Key

BotStar is a comprehensive chatbot platform for designing, developing, and training chatbots visually on Messenger and websites. It helps businesses automate conversations and customer interactions without coding.

31 Tools

Introduction

This guide walks you through connecting Botstar to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Botstar agent that can create and publish bots, manage bot attributes, update CMS entities and items, and control the live chat widget through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Botstar account through Composio's Botstar 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 Botstar with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Botstar MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Botstar account. It provides structured and secure access to your chatbot operations, so your agent can perform actions like managing live chat sessions, updating user details, retrieving app parameters, and sending data between webviews and your bot—all on your behalf.

  • Live chat session control: Programmatically open, close, or reinitialize the Botstar live chat widget to manage user interactions in real time.
  • Automated user profile updates: Let your agent update user details and profile attributes during an active chatbot conversation for a more personalized experience.
  • Webview data exchange: Seamlessly send responses from webviews back to the chatbot or retrieve parameters passed from the bot to your webview for dynamic content handling.
  • Custom callback registration: Set up onOpen and onClose event handlers so your agent can trigger actions whenever users interact with the chat window.
  • Application ID and configuration retrieval: Fetch essential Botstar application IDs and parameters for smooth widget initialization and advanced bot customization.

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: ["botstar"],
  });

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

  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 botstar, 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 Botstar 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 Botstar action and event your agent gets out of the box.

Create Bot

Tool to create a new bot in BotStar.

Create Bot Attribute

Tool to create a new bot attribute in BotStar.

Create CMS Entity

Tool to create a CMS entity in BotStar with a name and optional fields.

Create Entity Fields

Tool to create entity field(s) in BotStar CMS.

Create Entity Item

Tool to create a new entity item in BotStar CMS.

Create User Attributes

Tool to create custom user attributes in BotStar.

Delete Bot Attribute

Tool to delete a bot attribute by ID.

Delete CMS Entity

Tool to delete a CMS entity by ID.

Delete Entity Fields

Tool to delete entity field(s) from a CMS entity.

Delete Entity Item

Tool to delete an entity item from a CMS entity.

Get Bot

Tool to get your bot by bot ID.

Get BotStar Application IDs

Tool to retrieve the BotStar application ID (`appId`).

Get CMS Entity

Tool to get a specific CMS entity by ID.

Get Entity Item

Tool to retrieve a specific item from a CMS entity with all field values.

List Bot Attributes

Tool to get all bot attributes from BotStar.

List Bots

List bots associated with your account, with optional page and limit controls.

List CMS Entities

Tool to retrieve all CMS entities for a bot.

List Entity Items

List a page of CMS entity items, with optional filtering by name and status.

Livechat boot

Generate a JavaScript snippet to reinitialize the live chat widget with provided data after its initial load.

Close BotStar Livechat Widget

Generate a JavaScript snippet to hide the live chat window when the widget is configured in livechat or popup mode.

BotStar LiveChat onClose Callback

Generate a JavaScript snippet to register a callback for when the live chat window closes.

Livechat on open

Generate a JavaScript snippet to register a callback for when the live chat window opens.

Livechat open

Generate a JavaScript snippet to show the live chat window after the widget has been bootstrapped.

Livechat update

Generate a JavaScript snippet to update user details on the current live chat session.

Publish Bot to Live

Tool to publish a bot to live.

Update Bot Attribute

Tool to update a bot attribute in BotStar.

Update CMS Entity

Update the name of an existing BotStar CMS entity.

Update Entity Fields

Tool to update entity field(s) in BotStar CMS.

Update Entity Item

Tool to update a CMS entity item in BotStar.

Get BotStar Webview Parameter

Generate a JavaScript snippet to retrieve a parameter passed from the BotStar chatbot to the webview.

Webview send response

Generate a JavaScript snippet to send a response and custom outputs from a webview back to the BotStar chatbot.

FRAMEWORKS

How to build Botstar MCP Agent with another framework

Claude Code logo

Claude Code

Use Botstar MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Botstar MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Botstar MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Botstar MCP with Claude Agent SDK

Codex logo

Codex

Use Botstar MCP with Codex

OpenClaw logo

OpenClaw

Use Botstar MCP with OpenClaw

Hermes logo

Hermes

Use Botstar MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Botstar MCP with Atomic Agent

Google ADK logo

Google ADK

Use Botstar MCP with Google ADK

LangChain logo

LangChain

Use Botstar MCP with LangChain

Mastra AI logo

Mastra AI

Use Botstar MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Botstar MCP with LlamaIndex

CrewAI logo

CrewAI

Use Botstar MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Botstar MCP with Pydantic AI

AutoGen logo

AutoGen

Use Botstar MCP with AutoGen

FAQ

Frequently asked questions

Start with Botstar.It takes 30 seconds.

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

Start building