How to integrate Harvest MCP with Vercel AI SDK v6

This guide walks you through connecting Harvest to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Harvest agent that can create a new client for acme corp, log an expense for project 'website redesign', generate an invoice for hours worked this week through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Harvest account through Composio's Harvest MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Harvest logoHarvest
Oauth2

Harvest is a time-tracking and invoicing platform for teams and freelancers. It helps you log billable hours, manage projects, and streamline payments.

57 Tools

Introduction

This guide walks you through connecting Harvest to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Harvest agent that can create a new client for acme corp, log an expense for project 'website redesign', generate an invoice for hours worked this week through natural language commands.

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

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

Also integrate Harvest with

TL;DR

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

The Harvest MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Harvest account. It provides structured and secure access to your time-tracking, invoicing, and project management data, so your agent can create clients, log expenses, send invoices, record payments, and manage estimates automatically on your behalf.

  • Client and contact management: Seamlessly create new clients and add contacts to keep your client list up to date without manual entry.
  • Estimate creation and communication: Automatically generate new estimates, categorize line items, and send estimate messages or updates to clients.
  • Expense tracking automation: Log new expense entries against projects, ensuring accurate financial records and effortless cost tracking.
  • Streamlined invoicing and payments: Create professional invoices, categorize invoice items, send invoice notifications, and record payments as soon as they happen.
  • Project financial workflow optimization: Let your agent handle the full cycle—from creating clients to sending invoices and tracking payments—saving your team valuable time and reducing errors.

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: ["harvest"],
  });

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

  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 harvest, 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 Harvest 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 Harvest action and event your agent gets out of the box.

Create Client

Tool to create a new client.

Create Client Contact

Tool to create a new client contact.

Create Estimate

Tool to create a new estimate.

Create Estimate Item Category

Tool to create a new estimate item category in Harvest.

Create Estimate Message

Tool to create a new message for an estimate.

Create Expense

Tool to create a new expense entry.

Create Invoice

Tool to create a new invoice.

Create Invoice Item Category

Tool to create a new invoice item category.

Create Invoice Message

Creates a new message for an invoice in Harvest.

Create Invoice Payment

Tool to create a new payment on an invoice.

Create Project

Create a new project in Harvest.

Create Task

Creates a new task in Harvest.

Create Time Entry

Tool to create a new time entry.

Create User

Creates a new user in Harvest and sends an invitation email to the specified address.

Delete Client

Tool to delete a client.

Delete Client Contact

Permanently deletes a client contact from Harvest.

Delete Estimate

Tool to delete an estimate.

Delete Estimate Message

Tool to delete an estimate message.

Delete Invoice

Delete an invoice from Harvest.

Delete Invoice Item Category

Tool to delete an invoice item category from Harvest.

Delete Invoice Message

Tool to delete a message from an invoice.

Delete Invoice Payment

Tool to delete an invoice payment.

Delete Project

Tool to delete a project.

Delete Task

Tool to delete a task.

Delete Time Entry

Tool to delete a time entry.

Delete User

Tool to delete a user.

Get Client

Retrieves a specific client by ID from Harvest.

Get Company Info

Retrieves detailed information about the company associated with the authenticated Harvest account.

Get Estimate

Tool to retrieve a specific estimate by ID.

Get Invoice

Tool to retrieve a specific invoice by ID.

Get Project

Tool to retrieve a specific Harvest project by ID.

Get Task

Tool to retrieve a specific task by ID.

Get Time Entry

Tool to retrieve a single time entry by ID.

Get User

Tool to retrieve a specific user by ID.

List Client Contacts

Tool to list client contacts.

List Clients

Tool to list clients.

List Estimate Messages

Lists all messages associated with a specific estimate in Harvest.

List Expense Categories

Tool to list expense categories.

List Invoice Item Categories

Tool to retrieve invoice item categories.

List Invoice Messages

Tool to list messages associated with a given invoice.

List Invoice Payments

List all payments recorded for a specific invoice.

List Invoices

Tool to list invoices.

List projects

Tool to list projects.

List Tasks

Tool to list tasks.

List Time Entries

Tool to retrieve a list of time entries.

List Users

Tool to list users.

Update Client

Tool to update an existing client.

Update Client Contact

Tool to update a client contact.

Update Company Info

Updates company time tracking settings in Harvest.

Update Estimate

Tool to update an existing estimate.

Update Estimate Item Category

Updates an existing estimate item category's name in Harvest.

Update Expense

Tool to update an existing expense.

Update Invoice

Tool to update an existing invoice.

Update Project

Tool to update an existing project.

Update Task

Tool to update an existing task.

Update Time Entry

Tool to update an existing time entry.

Update User

Tool to update an existing user.

FAQ

Frequently asked questions

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

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

Start with Harvest.It takes 30 seconds.

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

Start building