SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Harvest MCP with Autogen

Connect Autogen to Harvest MCP. Create a new client for acme corp, log an expense for project 'website redesign', and more using natural language, with authentication handled for you.

Get started for freeGet a demo
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 AutoGen using the Composio tool router. By the end, you'll have a working Harvest agent that can log time entries, create invoices and estimates, record payments and expenses, and manage clients and projects through natural language commands.

This guide will help you understand how to give your AutoGen 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

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Harvest
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Harvest tools
  • Run a live chat loop where you ask the agent to perform Harvest operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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 step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Harvest account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
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 dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Harvest via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Harvest connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Harvest session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["harvest"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Harvest tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Harvest assistant agent with MCP tools
    agent = AssistantAgent(
        name="harvest_assistant",
        description="An AI assistant that helps with Harvest operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Harvest tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Harvest related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Harvest tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Harvest and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Harvest session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["harvest"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Harvest assistant agent with MCP tools
        agent = AssistantAgent(
            name="harvest_assistant",
            description="An AI assistant that helps with Harvest operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Harvest related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Harvest through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Harvest, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
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.

FRAMEWORKS

How to build Harvest MCP Agent with another framework

Claude Code logo

Claude Code

Use Harvest MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Harvest MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Harvest MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Harvest MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Harvest MCP with Grok Bot

Codex logo

Codex

Use Harvest MCP with Codex

OpenClaw logo

OpenClaw

Use Harvest MCP with OpenClaw

Hermes logo

Hermes

Use Harvest MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Harvest MCP with Atomic Agent

Google ADK logo

Google ADK

Use Harvest MCP with Google ADK

LangChain logo

LangChain

Use Harvest MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Harvest MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Harvest MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Harvest MCP with LlamaIndex

CrewAI logo

CrewAI

Use Harvest MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Harvest MCP with Pydantic AI

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. Autogen 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