How to integrate Nozbe Teams MCP with Vercel AI SDK v6

This guide walks you through connecting Nozbe Teams to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Nozbe Teams agent that can create a new project called 'q3 planning', assign all overdue tasks to sarah, list incomplete tasks in marketing project through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Nozbe Teams account through Composio's Nozbe Teams MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Nozbe Teams logoNozbe Teams
Api Key

Nozbe Teams is a cloud-based task management tool for individuals and teams. It helps you organize, track, and manage all your group tasks in one place.

48 Tools

Introduction

This guide walks you through connecting Nozbe Teams to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Nozbe Teams agent that can create a new project called 'q3 planning', assign all overdue tasks to sarah, list incomplete tasks in marketing project through natural language commands.

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

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

Also integrate Nozbe Teams with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

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

The Nozbe Teams MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Nozbe Teams account. It provides structured and secure access to your projects, tasks, comments, tags, team members, and teams, so your agent can review projects, create and update tasks, add comments, assign tags, and manage work on your behalf.

  • Project planning and updates: Have your agent list and review accessible projects, update project details, or delete projects you no longer need.
  • Task creation and management: Let the agent create tasks, review existing work, update task details, and remove tasks when plans change.
  • Task comments and collaboration: Direct your agent to add comments to tasks or delete comments that are no longer relevant.
  • Tag organization: Instruct your agent to list available tags and assign the right tags to tasks for clearer organization.
  • Team and user visibility: Have your agent review accessible users and team details, or update user information when needed.

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: ["nozbe_teams"],
  });

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

  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 nozbe_teams, 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 Nozbe Teams 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 Nozbe Teams action and event your agent gets out of the box.

Create Attachment

Tool to add attachment metadata to a comment.

Create Comment

Tool to add a comment to a task in Nozbe Teams.

Create Project Section

Tool to create a new project section in Nozbe Teams.

Create Reminder

Tool to add a reminder to a task in Nozbe Teams.

Create Tag Assignment

Tool to add a tag assignment to a task.

Create Task

Tool to create a new task in Nozbe Teams.

Create Team Member

Tool to add a team member in Nozbe Teams.

Create User

Tool to create a new placeholder user in Nozbe Teams.

Delete Comment

Tool to permanently delete a comment by its ID.

Delete Project

Tool to delete a project in Nozbe Teams by its ID.

Delete Reminder

Tool to delete a reminder by its unique ID.

Delete Tag Assignment

Tool to delete a tag assignment by its ID.

Delete Task

Tool to delete a task in Nozbe Teams by its ID.

Get Attachment

Tool to get attachment metadata by its ID.

Get Comment by ID

Tool to retrieve a comment by its ID from Nozbe Teams.

Get Project by ID

Tool to retrieve a project by its ID from Nozbe Teams.

Get Project Access

Tool to retrieve project access details by ID.

Get Project Section

Tool to retrieve a project section by ID from Nozbe Teams.

Get Reminder

Tool to get a reminder by ID from Nozbe Teams.

Get Tag

Tool to get a tag by ID from Nozbe Teams.

Get Tag Assignment

Tool to retrieve a tag assignment by its ID.

Get Task by ID

Tool to retrieve a task by its ID from Nozbe Teams.

Get Task Event

Tool to get a task event by ID.

Get Team by ID

Tool to retrieve a team by its ID from Nozbe Teams.

Get Team Member by ID

Tool to retrieve a team member by ID from Nozbe Teams.

Get User by ID

Tool to retrieve a user by their ID from Nozbe Teams.

List Comment Attachments

Tool to get all attachments related to a specific comment in Nozbe Teams.

List Comments

Tool to get accessible comments with optional filtering by task_id and pagination support.

List Group Assignments

Tool to get accessible group assignments from Nozbe Teams.

List Project Accesses

Tool to get accessible project accesses in Nozbe Teams.

List Project Groups

Tool to get accessible project groups from Nozbe Teams.

List Projects

Tool to retrieve accessible projects with optional filtering.

List Project Sections

Tool to retrieve accessible project sections with optional filtering.

List Reminders

Tool to get accessible reminders from Nozbe Teams.

List Tag Assignments

Tool to get accessible tag assignments with optional filtering by tag_id or task_id.

List Tags

Tool to get accessible tags from Nozbe Teams.

List Task Events

Tool to get accessible task events from Nozbe Teams.

List Tasks

Tool to retrieve accessible tasks from Nozbe Teams.

List Users

Tool to retrieve accessible users from Nozbe Teams.

Poll for new tasks

Tool to poll for new tasks created since the last call.

Poll Updated Tasks

Tool to poll for tasks that have been updated since the last call.

Update Comment

Tool to update an existing comment in Nozbe Teams.

Update Project

Tool to update a project in Nozbe Teams.

Update Project Access

Tool to update project access permissions in Nozbe Teams.

Update Task

Tool to update a task in Nozbe Teams.

Update Team

Tool to update a team in Nozbe Teams.

Update Team Member

Tool to update a team member in Nozbe Teams.

Update User

Tool to update a user in Nozbe Teams.

FRAMEWORKS

How to build Nozbe Teams MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Nozbe Teams MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Nozbe Teams MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Nozbe Teams MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Nozbe Teams MCP with Claude Cowork

Codex logo

Codex

Use Nozbe Teams MCP with Codex

OpenClaw logo

OpenClaw

Use Nozbe Teams MCP with OpenClaw

Hermes logo

Hermes

Use Nozbe Teams MCP with Hermes

CLI logo

CLI

Use Nozbe Teams MCP with CLI

Google ADK logo

Google ADK

Use Nozbe Teams MCP with Google ADK

LangChain logo

LangChain

Use Nozbe Teams MCP with LangChain

Mastra AI logo

Mastra AI

Use Nozbe Teams MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Nozbe Teams MCP with LlamaIndex

CrewAI logo

CrewAI

Use Nozbe Teams MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Nozbe Teams.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies