How to integrate Harvest MCP with LlamaIndex

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Harvest Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Harvest to LlamaIndex 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, send an estimate message to a client through natural language commands.

This guide will help you understand how to give your LlamaIndex 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.

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Harvest
  • Connect LlamaIndex to the Harvest MCP server
  • Build a Harvest-powered agent using LlamaIndex
  • Interact with Harvest through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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.

Supported Tools & Triggers

Tools
Create ClientTool to create a new client.
Create Client ContactTool to create a new client contact.
Create EstimateTool to create a new estimate.
Create Estimate Item CategoryTool to create a new estimate item category in harvest.
Create Estimate MessageTool to create a new message for an estimate.
Create ExpenseTool to create a new expense entry.
Create InvoiceTool to create a new invoice.
Create Invoice Item CategoryTool to create a new invoice item category.
Create Invoice MessageTool to create a new message for an invoice.
Create Invoice PaymentTool to create a new payment on an invoice.
Create ProjectTool to create a new project.
Create TaskTool to create a new task.
Create Time EntryTool to create a new time entry.
Create UserTool to create a new user.
Delete ClientTool to delete a client.
Delete Client ContactTool to delete a client contact.
Delete EstimateTool to delete an estimate.
Delete Estimate MessageTool to delete an estimate message.
Delete InvoiceTool to delete an invoice.
Delete Invoice Item CategoryTool to delete an invoice item category.
Delete Invoice MessageTool to delete a message from an invoice.
Delete Invoice PaymentTool to delete an invoice payment.
Delete ProjectTool to delete a project.
Delete TaskTool to delete a task.
Delete Time EntryTool to delete a time entry.
Delete UserTool to delete a user.
Get ClientTool to retrieve a specific client by id.
Get Client ContactTool to retrieve a specific client contact.
Get Company InfoTool to retrieve information about the authenticated user's company.
Get EstimateTool to retrieve a specific estimate by id.
Get InvoiceTool to retrieve a specific invoice by id.
Get ProjectTool to retrieve a specific harvest project by id.
Get TaskTool to retrieve a specific task by id.
Get Time EntryTool to retrieve a single time entry by id.
Get UserTool to retrieve a specific user by id.
List Client ContactsTool to list client contacts.
List ClientsTool to list clients.
List Estimate MessagesTool to list messages for an estimate.
List Expense CategoriesTool to list expense categories.
List Invoice Item CategoriesTool to retrieve invoice item categories.
List Invoice MessagesTool to list messages associated with a given invoice.
List Invoice PaymentsTool to retrieve payments for a specific invoice.
List InvoicesTool to list invoices.
List projectsTool to list projects.
List TasksTool to list tasks.
List Time EntriesTool to retrieve a list of time entries.
List UsersTool to list users.
Update ClientTool to update an existing client.
Update Client ContactTool to update a client contact.
Update Company InfoTool to update information about the company.
Update EstimateTool to update an existing estimate.
Update Estimate Item CategoryTool to update an estimate item category.
Update ExpenseTool to update an existing expense.
Update InvoiceTool to update an existing invoice.
Update ProjectTool to update an existing project.
Update TaskTool to update an existing task.
Update Time EntryTool to update an existing time entry.
Update UserTool to update an existing user.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Harvest account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Harvest

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Harvest access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called harvest_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["harvest"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Harvest actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Harvest actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, harvest)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Harvest tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Harvest database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Harvest

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Harvest, then start asking questions.

Complete Code

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

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["harvest"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Harvest actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Harvest actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Harvest to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Harvest tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Harvest MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Harvest MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Harvest MCP with Claude Agent SDK

Google ADK

Google ADK

Use Harvest MCP with Google ADK

LangChain

LangChain

Use Harvest MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Harvest MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Harvest MCP with Mastra AI

CrewAI

CrewAI

Use Harvest MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Harvest MCP?

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.

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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.

Can I manage the permissions and scopes for Harvest while using Tool Router?

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.

How safe is my data with Composio Tool Router?

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.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free