How to Use the Harvest MCP in OpenAI Agents SDK

Q: What's the best way to handle invoicing for multiple projects with Harvest and the OpenAI Agents SDK?

Have your agent first call listprojects to get IDs for a specific client. Then, it can loop through those projects, calling listtimeentries for each one to gather all billable hours before creating a single, consolidated invoice.

Build production-ready billing agents with the OpenAI Agents SDK. Automate your Harvest invoicing with built-in safety checks and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harvest MCP to OpenAI Agents SDK

Create your Vinkius account to connect Harvest to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Harvest with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Clients with Guardrails

This server exposes tools to fully manage your Harvest client list. Your agent can add new customers with `create_client`, fetch details with `get_client`, and even remove them with `delete_client`. Here’s the key part: the OpenAI Agents SDK lets you add guardrails. You can require human-in-the-loop confirmation before your agent runs a destructive action like `delete_client`. That means no more accidental deletions from an overzealous agent.

Automate Invoicing with Full Traceability

Turn tracked hours into draft invoices, automatically. An agent can use `list_time_entries` and `list_projects` to gather all unbilled hours for a specific client. Then, it uses `create_invoice` to generate a perfect draft in Harvest, ready for you to review and send. Because you're using the OpenAI Agents SDK, you get a complete execution trace for every step. The dashboard shows you exactly which time entries the agent picked and how it constructed the invoice. You'll always know why your agent did what it did.

Give Your Agent Context with this MCP Server

An agent is only as good as the information it has. This MCP Server gives it the tools to understand your Harvest account before it acts. It can run `list_clients` to see if a customer already exists before trying to create a duplicate. It can also check for active projects with `list_projects` or review past bills with `list_invoices`. This context-gathering step prevents errors and makes your agent's actions much more reliable. Your agent stops guessing and starts knowing.

Setup guide

Set up Harvest MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Harvest tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Harvest tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Harvest tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Harvest Agent",
            instructions="You have access to Harvest tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Harvest. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Harvest now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Harvest MCP in OpenAI Agents SDK

First, install the SDK. Then, point it to the Vinkius endpoint for this Harvest server. The tools are discovered automatically, so your agent can immediately start using functions like `create_client` and `list_invoices`.

Yes. While the agent can see all available tools, you define which ones it's permitted to execute in your agent's configuration. You can grant it access to `list_time_entries` but deny it `delete_client`, for example.

Have your agent first call `list_projects` to get IDs for a specific client. Then, it can loop through those projects, calling `list_time_entries` for each one to gather all billable hours before creating a single, consolidated invoice.

Absolutely. The OpenAI Agents SDK is built for observability. Every tool call your agent makes to the MCP server is logged and traced, giving you a clear view of its actions and reasoning.

The server processes client names, invoice details, and time entry records. Vinkius runs each MCP Server in a dedicated, ephemeral sandbox. Your data is only held in memory for the duration of the API call and is never logged or stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript