# How to integrate Harvest MCP with LlamaIndex

```json
{
  "title": "How to integrate Harvest MCP with LlamaIndex",
  "toolkit": "Harvest",
  "toolkit_slug": "harvest",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/harvest/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/harvest/framework/llama-index.md",
  "updated_at": "2026-05-12T10:14:39.260Z"
}
```

## 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 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.

## Also integrate Harvest with

- [OpenAI Agents SDK](https://composio.dev/toolkits/harvest/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/harvest/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/harvest/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/harvest/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/harvest/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/harvest/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/harvest/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/harvest/framework/cli)
- [Google ADK](https://composio.dev/toolkits/harvest/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/harvest/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/harvest/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/harvest/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/harvest/framework/crew-ai)

## 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

| Tool slug | Name | Description |
|---|---|---|
| `HARVEST_CREATE_CLIENT` | Create Client | Tool to create a new client. Use after gathering client details to register a new client in Harvest. |
| `HARVEST_CREATE_CLIENT_CONTACT` | Create Client Contact | Tool to create a new client contact. Use when you need to add a contact under an existing client. Call after you've retrieved or confirmed the client_id. |
| `HARVEST_CREATE_ESTIMATE` | Create Estimate | Tool to create a new estimate. Use after gathering client and line item details. |
| `HARVEST_CREATE_ESTIMATE_ITEM_CATEGORY` | Create Estimate Item Category | Tool to create a new estimate item category in Harvest. Use after deciding to categorize line items within an estimate. |
| `HARVEST_CREATE_ESTIMATE_MESSAGE` | Create Estimate Message | Tool to create a new message for an estimate. Use when you have an estimate ID and want to send a message or run an event (send, accept, decline, re-open) on the estimate. |
| `HARVEST_CREATE_EXPENSE` | Create Expense | Tool to create a new expense entry. Use when recording costs against projects. Ensure either units or total_cost is provided. |
| `HARVEST_CREATE_INVOICE` | Create Invoice | Tool to create a new invoice. Use when you have gathered all invoice details and need to bill a client in Harvest. |
| `HARVEST_CREATE_INVOICE_ITEM_CATEGORY` | Create Invoice Item Category | Tool to create a new invoice item category. Use after you have decided on the category name to register it in Harvest. |
| `HARVEST_CREATE_INVOICE_MESSAGE` | Create Invoice Message | Creates a new message for an invoice in Harvest. Use this to send invoice notifications to clients, create draft messages, or change invoice states (close/reopen). Requires a valid invoice ID. The invoice must be in the appropriate state for the requested event_type. |
| `HARVEST_CREATE_INVOICE_PAYMENT` | Create Invoice Payment | Tool to create a new payment on an invoice. Use when recording a payment against an existing invoice. |
| `HARVEST_CREATE_PROJECT` | Create Project | Create a new project in Harvest. A project is a container for tracking time, expenses, and invoices for a specific client engagement. Required: You must provide a valid client_id (use list_clients or create_client first), project name, and billing configuration (is_billable, bill_by, budget_by). Common use cases: - Time & Materials: is_billable=true, bill_by="Tasks", budget_by="project" - Fixed Fee: is_billable=true, bill_by="Project", budget_by="none", is_fixed_fee=true - Internal/Non-billable: is_billable=false, bill_by="none", budget_by="none" |
| `HARVEST_CREATE_TASK` | Create Task | Creates a new task in Harvest. Tasks are reusable activity types (e.g., "Development", "Design", "Consulting") that can be assigned to projects for time tracking. Use this to define billable or non-billable work categories that your team will track time against. |
| `HARVEST_CREATE_TIME_ENTRY` | Create Time Entry | Tool to create a new time entry. Use when logging hours for a project by specifying start/end times or duration. |
| `HARVEST_CREATE_USER` | Create User | Creates a new user in Harvest and sends an invitation email to the specified address. Use this action to add team members to your Harvest account. You can specify their role, permissions, rates, and whether they are employees or contractors. The user will receive an invitation email to activate their account. Required: first_name, last_name, and email. Optional: timezone, access roles, rates, weekly capacity, and business roles. |
| `HARVEST_DELETE_CLIENT` | Delete Client | Tool to delete a client. Use when you need to remove a client that has no associated projects, invoices, or estimates. Call after confirming the client_id exists and has no dependent resources. |
| `HARVEST_DELETE_CLIENT_CONTACT` | Delete Client Contact | Permanently deletes a client contact from Harvest. Use when you need to remove a contact that is no longer relevant. Requires Administrator or Manager permissions. The deletion cannot be undone, so verify the contact_id before calling. |
| `HARVEST_DELETE_ESTIMATE` | Delete Estimate | Tool to delete an estimate. Use when you need to remove an estimate that is no longer needed. Call after confirming the estimate_id exists and has no dependent resources. |
| `HARVEST_DELETE_ESTIMATE_MESSAGE` | Delete Estimate Message | Tool to delete an estimate message. Use when you need to remove a message from an estimate. Call after confirming estimate_id and message_id are correct. |
| `HARVEST_DELETE_INVOICE` | Delete Invoice | Delete an invoice from Harvest. Removes the specified invoice permanently. Requires Administrator or Manager permissions with invoice editing access. |
| `HARVEST_DELETE_INVOICE_ITEM_CATEGORY` | Delete Invoice Item Category | Tool to delete an invoice item category from Harvest. Returns 200 OK on success with no response body. Important: Deletion is only possible if both use_as_service and use_as_expense are false. Categories actively used for billable hours or expenses cannot be deleted. Use when you need to remove an obsolete or unused invoice item category. Requires Admin or Project Manager permissions. |
| `HARVEST_DELETE_INVOICE_MESSAGE` | Delete Invoice Message | Tool to delete a message from an invoice. Use when you need to remove a specific message that is no longer relevant. Call after confirming the invoice_id and message_id. |
| `HARVEST_DELETE_INVOICE_PAYMENT` | Delete Invoice Payment | Tool to delete an invoice payment. Use when you need to remove a payment from an invoice after confirming payment details. |
| `HARVEST_DELETE_PROJECT` | Delete Project | Tool to delete a project. Use when you need to remove a project and all its associated time entries and expenses; invoices remain intact. Call after confirming the project_id exists. |
| `HARVEST_DELETE_TASK` | Delete Task | Tool to delete a task. Use when you need to remove a task that has no associated time entries. Call after confirming the task_id exists and has no dependent time entries. |
| `HARVEST_DELETE_TIME_ENTRY` | Delete Time Entry | Tool to delete a time entry. Use when removing an existing time entry that is deletable (not closed or on archived projects/tasks). Call after confirming the time_entry_id exists. |
| `HARVEST_DELETE_USER` | Delete User | Tool to delete a user. Use when you need to remove a user that has no associated time entries or expenses. Call after confirming the user_id exists and has no dependent time entries or expenses. |
| `HARVEST_GET_CLIENT` | Get Client | Retrieves a specific client by ID from Harvest. Use this to get detailed information about a client including their name, active status, address, currency, and timestamps. Returns complete client details needed for invoicing, reporting, or verifying client information. |
| `HARVEST_GET_COMPANY_INFO` | Get Company Info | Retrieves detailed information about the company associated with the authenticated Harvest account. This endpoint returns comprehensive company settings including: - Basic information (name, domain, active status) - Time tracking preferences (format, week start day, timer type) - Localization settings (date/time format, currency, separators) - Feature flags (expenses, invoices, estimates, approvals, team scheduling) - Weekly capacity and other operational settings No parameters required. Use this to understand company configuration before performing other operations. |
| `HARVEST_GET_ESTIMATE` | Get Estimate | Tool to retrieve a specific estimate by ID. Use after confirming the estimate ID. Example: "Get estimate with ID 123456". |
| `HARVEST_GET_INVOICE` | Get Invoice | Tool to retrieve a specific invoice by ID. Use when you need the full details of an invoice after selecting or creating it. Example: 'Get invoice with ID 13150378.' |
| `HARVEST_GET_PROJECT` | Get Project | Tool to retrieve a specific Harvest project by ID. Use when you have a project ID and need its details. |
| `HARVEST_GET_TASK` | Get Task | Tool to retrieve a specific task by ID. Use when you have a task ID and need its detailed information. |
| `HARVEST_GET_TIME_ENTRY` | Get Time Entry | Tool to retrieve a single time entry by ID. Use when you have a specific time entry ID and need its full details. |
| `HARVEST_GET_USER` | Get User | Tool to retrieve a specific user by ID. Use after obtaining a valid user ID (for example via List Users). Example: "Get details of user 3230547". |
| `HARVEST_LIST_CLIENT_CONTACTS` | List Client Contacts | Tool to list client contacts. Use when you need to retrieve contacts with optional filtering and pagination. |
| `HARVEST_LIST_CLIENTS` | List Clients | Tool to list clients. Use when you need to retrieve a paginated list of clients from Harvest. Ensure you have a valid access token in metadata before calling. |
| `HARVEST_LIST_ESTIMATE_MESSAGES` | List Estimate Messages | Lists all messages associated with a specific estimate in Harvest. Returns messages sorted by creation date (most recent first). Use this tool when you need to: - View communication history for an estimate - Check what messages have been sent to clients regarding an estimate - Track events that occurred on an estimate (send, accept, decline, re-open) - Filter messages by update time to find recent communications Requires a valid estimate_id. Supports pagination via per_page parameter (default 2000, max 2000). |
| `HARVEST_LIST_EXPENSE_CATEGORIES` | List Expense Categories | Tool to list expense categories. Use when you need to retrieve a paginated list of expense categories, optionally filtering by active status or last update timestamp. |
| `HARVEST_LIST_INVOICE_ITEM_CATEGORIES` | List Invoice Item Categories | Tool to retrieve invoice item categories. Use when you need to fetch a paginated list of invoice item categories in Harvest. |
| `HARVEST_LIST_INVOICE_MESSAGES` | List Invoice Messages | Tool to list messages associated with a given invoice. Use when you need to retrieve invoice messages with optional filtering by update time and pagination. |
| `HARVEST_LIST_INVOICE_PAYMENTS` | List Invoice Payments | List all payments recorded for a specific invoice. Returns payment details including amounts, dates, payment gateway information, and who recorded each payment. Supports filtering by updated_since date and pagination. Returns an empty list if the invoice has no payments. |
| `HARVEST_LIST_INVOICES` | List Invoices | Tool to list invoices. Use when you need to retrieve invoices filtered by client, project, date range, or state. Example: 'List invoices for client 5735776 from 2023-01-01 to 2023-01-31.' |
| `HARVEST_LIST_PROJECTS` | List projects | Tool to list projects. Use when you need to retrieve a paginated list of projects from Harvest. Ensure a valid access token is present in metadata before calling. Results span multiple pages; check total_pages in the response and increment page to retrieve all projects. Large result sets may be returned as remote files rather than inline JSON; use structure_info to parse the response correctly. |
| `HARVEST_LIST_TASKS` | List Tasks | Tool to list tasks. Use when you need to retrieve a paginated list of tasks from Harvest. Ensure you have a valid access token in metadata before calling. Response includes `total_pages` to iterate all pages when task count exceeds `per_page`. |
| `HARVEST_LIST_TIME_ENTRIES` | List Time Entries | Tool to retrieve a list of time entries. Use when you need to fetch tracked hours with filters or date ranges for reporting or invoicing. Example: "List time entries for project 123 between 2023-01-01 and 2023-01-31". |
| `HARVEST_LIST_USERS` | List Users | Tool to list users. Use when you need to retrieve a paginated list of users from Harvest. |
| `HARVEST_UPDATE_CLIENT` | Update Client | Tool to update an existing client. Use after retrieving client details to modify its properties. Supports partial updates; omit fields to leave them unchanged. |
| `HARVEST_UPDATE_CLIENT_CONTACT` | Update Client Contact | Tool to update a client contact. Use when you have a contact_id and need to modify its details. |
| `HARVEST_UPDATE_COMPANY_INFO` | Update Company Info | Updates company time tracking settings in Harvest. This endpoint allows modification of two company settings: 1. wants_timestamp_timers - Controls whether time is tracked via duration or start/end times 2. weekly_capacity - Sets the expected working hours per week (in seconds) Returns the complete updated company object. Requires admin permissions. Note: Other company settings (name, timezone, currency, date/time formats, color scheme, etc.) cannot be modified via the API and must be changed through the Harvest web interface. |
| `HARVEST_UPDATE_ESTIMATE` | Update Estimate | Tool to update an existing estimate. Use when you need to modify specific fields of an estimate; omit parameters to leave other fields unchanged. |
| `HARVEST_UPDATE_ESTIMATE_ITEM_CATEGORY` | Update Estimate Item Category | Updates an existing estimate item category's name in Harvest. Estimate item categories are used to organize line items within estimates. Provide the category ID and the new name you want to set. |
| `HARVEST_UPDATE_EXPENSE` | Update Expense | Tool to update an existing expense. Use after retrieving an expense to modify project, category, date, cost, or delete a receipt; omit fields to leave unchanged. |
| `HARVEST_UPDATE_INVOICE` | Update Invoice | Tool to update an existing invoice. Use after retrieving invoice details to modify its fields. Supports partial updates; omit fields to leave unchanged. |
| `HARVEST_UPDATE_PROJECT` | Update Project | Tool to update an existing project. Use when you need to modify one or more fields of a project by its ID. Invoke after confirming the project ID and desired changes. |
| `HARVEST_UPDATE_TASK` | Update Task | Tool to update an existing task. Use after retrieving task details to modify its attributes such as name, billing defaults, or status. Supports partial updates; omit fields to leave them unchanged. |
| `HARVEST_UPDATE_TIME_ENTRY` | Update Time Entry | Tool to update an existing time entry. Use after retrieving the entry to adjust hours, notes, project, or task details. Supports partial updates; omit fields to leave unchanged. |
| `HARVEST_UPDATE_USER` | Update User | Tool to update an existing user. Use when you need to modify a user's profile or settings after confirming the user ID. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Harvest MCP server is an implementation of the Model Context Protocol that connects your AI agent to Harvest. It provides structured and secure access so your agent can perform Harvest operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. 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

### 1. Getting API Keys for OpenAI, Composio, and Harvest

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

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

### 4. Import modules

No description provided.
```python
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()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
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")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

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.
```python
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)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["harvest"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Harvest actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
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}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

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
```python
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!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Harvest, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
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!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["harvest"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Harvest actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## 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](https://composio.dev/toolkits/harvest/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/harvest/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/harvest/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/harvest/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/harvest/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/harvest/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/harvest/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/harvest/framework/cli)
- [Google ADK](https://composio.dev/toolkits/harvest/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/harvest/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/harvest/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/harvest/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/harvest/framework/crew-ai)

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page.
- [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes.
- [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights.
- [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement.

## Frequently Asked Questions

### 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.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)