SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Supportbee MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Supportbee MCP. Archive all tickets resolved this week, assign new tickets to the support team, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Supportbee logoSupportbee
Api Key

SupportBee is a web-based email support tool for organizing customer support emails. It streamlines team collaboration and keeps customer conversations efficient and accessible.

41 Tools

Introduction

This guide walks you through connecting Supportbee to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Supportbee agent that can create and reply to tickets, assign tickets to teams, label and archive tickets, manage snippets, and check response time reports through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Supportbee account through Composio's Supportbee 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 Supportbee 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 Supportbee integration
  • Using Composio's Tool Router to dynamically load and access Supportbee 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 Supportbee MCP server, and what's possible with it?

The Supportbee MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Supportbee account. It provides structured and secure access to your support ticketing system, so your agent can perform actions like creating and replying to tickets, managing team assignments, organizing tickets, and automating support workflows on your behalf.

  • Automated ticket creation and updates: Instantly open new support tickets, update their content, or post replies to customer inquiries without leaving your workflow.
  • Team assignment and ticket routing: Direct your agent to assign tickets to the right team or agent, ensuring every request is handled by the appropriate group.
  • Archiving and deleting tickets: Keep your helpdesk organized by having the agent archive resolved tickets or permanently remove unwanted ones from the system.
  • Reusable response snippets: Let your agent create, manage, and delete response templates so your team can reply faster and more consistently.
  • Rule-based workflow automation: Empower your agent to create new automation rules that streamline ticket routing, escalation, and handling based on custom conditions.

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: ["supportbee"],
  });

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

  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 supportbee, 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 Supportbee 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 Supportbee action and event your agent gets out of the box.

Add Label to Ticket

Tool to add a label to a ticket.

Archive SupportBee Ticket

Tool to archive a SupportBee ticket by its ID.

Assign Ticket to Team

Assigns a ticket to a team in SupportBee.

Create Ticket Comment

Creates an internal comment on a ticket in SupportBee.

Create Consequence

Creates a new consequence for rules automation in SupportBee.

Create Forwarding Email

Create a new forwarding email address for the company in SupportBee.

Create Filter

Creates a SupportBee filter by linking an existing rule with a consequence.

Create Rule

Submits a SupportBee automation rule with conditions and action entries and returns the rule ID.

Create Snippet

Create a reusable snippet (canned response) in SupportBee.

Create SupportBee Ticket

Creates a new support ticket in SupportBee with a subject, content, and requester details.

Create Ticket Reply

Create a reply to a support ticket in SupportBee.

Create SupportBee User

Invites a new user to your SupportBee account.

Delete Snippet

Permanently delete a snippet by its ID from SupportBee.

Delete SupportBee Ticket

Permanently delete a trashed ticket from SupportBee.

Fetch Forwarding Emails

Retrieves the company's forwarding email addresses configured in SupportBee.

Fetch SupportBee Labels

Tool to retrieve all custom labels.

Fetch Snippets

Fetches saved response snippets (canned responses/templates) from SupportBee.

Fetch SupportBee Teams

Retrieves all teams in the SupportBee account.

Get Avg First Response Time Report

Tool to retrieve average first response time data points over time.

Get Replies Count Report

Retrieves replies count report data for the company.

Get Ticket

Tool to retrieve a specific SupportBee ticket by its ID.

Get Tickets Count Report

Requests a SupportBee ticket count report for a specified date range, with optional agent, team, and label parameters.

List Ticket Comments

Retrieves all internal comments (private agent notes) for a specific ticket.

List Ticket Replies

Lists all replies on a specific support ticket in SupportBee.

List Tickets

Tool to list tickets from SupportBee.

List SupportBee Users

Lists SupportBee users or customer groups, with options to select the type and include invited agents.

Mark SupportBee Ticket as Answered

Marks a SupportBee ticket as answered by adding the 'answered' status.

Mark SupportBee Ticket as Spam

Tool to mark a SupportBee ticket as spam.

Mark SupportBee Ticket as Unanswered

Marks a SupportBee ticket as unanswered by removing its 'answered' status.

Remove Label From Ticket

Tool to remove a label from a ticket.

Search SupportBee Tickets

Tool to search SupportBee tickets.

Show Ticket Reply

Requests a specific SupportBee ticket reply by ticket and reply IDs.

Show SupportBee User or Customer Group

Retrieves details of a SupportBee user (agent/admin) or customer group by their ID.

Trash SupportBee Ticket

Tool to trash a SupportBee ticket by its ID.

Unarchive SupportBee Ticket

Tool to unarchive a SupportBee ticket by its ID.

Unassign Ticket from Team

Tool to un-assign a ticket from its assigned team.

Unassign User From Ticket

Tool to un-assign a ticket from its assigned user/agent.

Unmark SupportBee Ticket as Spam

Tool to unmark a SupportBee ticket as spam.

Untrash SupportBee Ticket

Restores a trashed SupportBee ticket back to active status.

Update Snippet

Update an existing SupportBee snippet (canned response) by ID.

Update SupportBee User

Update an existing SupportBee user's name, email, role, avatar, or signature by ID.

FRAMEWORKS

How to build Supportbee MCP Agent with another framework

Claude Code logo

Claude Code

Use Supportbee MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Supportbee MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Supportbee MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Supportbee MCP with Claude Agent SDK

Codex logo

Codex

Use Supportbee MCP with Codex

OpenClaw logo

OpenClaw

Use Supportbee MCP with OpenClaw

Hermes logo

Hermes

Use Supportbee MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Supportbee MCP with Atomic Agent

Google ADK logo

Google ADK

Use Supportbee MCP with Google ADK

LangChain logo

LangChain

Use Supportbee MCP with LangChain

Mastra AI logo

Mastra AI

Use Supportbee MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Supportbee MCP with LlamaIndex

CrewAI logo

CrewAI

Use Supportbee MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Supportbee MCP with Pydantic AI

AutoGen logo

AutoGen

Use Supportbee MCP with AutoGen

FAQ

Frequently asked questions

Start with Supportbee.It takes 30 seconds.

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

Start building