How to integrate Timely MCP with Vercel AI SDK v6

This guide walks you through connecting Timely to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Timely agent that can get your timely account billing details, set up webhook for new time entries, retrieve account info for client project through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Timely account through Composio's Timely MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Timely logoTimely
Oauth2

Timely is an automatic time-tracking platform that seamlessly records work across apps, calendars, and devices. It helps you create detailed timesheets and gain productivity insights without manual input.

41 Tools

Introduction

This guide walks you through connecting Timely to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Timely agent that can get your timely account billing details, set up webhook for new time entries, retrieve account info for client project through natural language commands.

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

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

Also integrate Timely with

TL;DR

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

The Timely MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Timely account. It provides structured and secure access to your time-tracking data, so your agent can perform actions like retrieving account information, managing webhooks, and integrating time logs with other workflows on your behalf.

  • Account information retrieval: Instantly fetch up-to-date details about your Timely account, including billing, activity, and user info, for streamlined reporting or troubleshooting.
  • Automated webhook setup: Direct your agent to create new webhooks for your account, enabling real-time integration with external apps and automated event notifications.
  • Seamless workflow automation: Connect Timely events to other services or agents by configuring webhooks, so you can automate time-tracking updates or project triggers.
  • Centralized time management: Allow your agent to coordinate between Timely and your other productivity tools by securely accessing and sharing account data as 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: ["timely"],
  });

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

  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 timely, 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 Timely 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 Timely action and event your agent gets out of the box.

Create Client

Tool to create a new client in the specified Timely account.

Create Day Locking

Tool to create a day locking entry that prevents editing of time entries for specific dates and users.

Create Label

Tool to create a new label in the specified Timely account.

Create report

Tool to generate reports for a Timely account with optional filters.

Create Team

Tool to create a new team in the specified Timely account.

Create Webhook

Tool to create a new webhook for the specified account.

Delete a label

Tool to delete a label by ID from a Timely account.

Delete a team

Tool to delete a team by its ID.

Delete Webhook

Tool to delete an existing webhook by its ID.

Filter reports

Tool to filter Timely reports based on date range, users, projects, labels, teams, and billing status.

Get activities

Tool to retrieve all activities (audit trail) for a Timely account.

Get Client

Tool to retrieve details of a specific client by its ID.

Get current user's permissions

Tool to retrieve the current user's permissions for a specified account.

Get current user

Tool to retrieve the currently authenticated user.

Retrieve a label

Tool to retrieve a label by ID from a Timely account.

Get project

Tool to retrieve a single project by its ID.

Retrieve a team

Tool to retrieve details of a specific team by its ID.

Retrieve a user

Tool to retrieve a user by ID from a Timely account.

Get user capacities

Tool to retrieve capacity information for a specific user in a Timely account.

Get user permissions

Tool to retrieve a user's permissions by their ID.

Get Webhook

Tool to retrieve a specific webhook by its ID.

List accounts

Retrieve all accessible Timely accounts for the authenticated user.

List clients

Tool to list all clients in a Timely account with optional filtering and sorting.

List events

Tool to list all events (time entries) in a Timely account with optional filtering by date range, users, and projects.

List forecasts

Tool to list all forecasts (tasks) in a Timely account with optional date filtering.

List labels

Tool to list all labels in a Timely account.

List project events

Tool to list all events (time entries) for a specific project in Timely.

List projects

Tool to list all projects in a Timely account with optional filtering and sorting.

List roles

Tool to list all available roles in a Timely account.

List teams

Tool to list all teams in the specified Timely account.

List user events

Tool to list all events (time entries) for a specific user in Timely.

List users

Tool to list all users in a Timely account with optional filtering and pagination.

List Webhooks

Tool to list all webhooks in the specified account.

Process bulk events

Tool to create, update, or delete multiple events in a single bulk operation.

Retrieve an account

Tool to retrieve details of a specific account by its ID.

Update a client

Tool to update an existing client by ID in Timely.

Update day locking settings

Tool to update day locking settings for specified users and dates.

Update a label

Tool to update a label by ID in a Timely account.

Update a project

Tool to update a project by ID in a Timely account.

Update a user

Tool to update a user by ID in a Timely account.

Update Webhook

Tool to update an existing webhook by ID.

FAQ

Frequently asked questions

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

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

Start with Timely.It takes 30 seconds.

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

Start building