How to Use the Homebase MCP in OpenAI Agents SDK

Q: How do I start using Homebase with the OpenAI Agents SDK?

First, install the SDK with pip. Then, create an MCPServerStreamableHttp instance pointing to your Vinkius endpoint URL. You pass that into the Agent constructor, and the tools are discovered automatically.

Q: Can my agent manage schedules across multiple business locations?

Yes. The first step is always to call listlocations to get the unique ID for each site. From there, your agent can loop through those IDs to run other tools like listscheduledshifts for each specific location.

Q: What's the best way to check labor costs against my budget with Homebase and the OpenAI Agents SDK?

Have your agent call listlaborbudgets to get the target numbers for a location. Then, use listtimecards to fetch the actual hours worked within a pay period. Your agent can then compare the two and flag any discrepancies.

Build production-ready scheduling agents with the OpenAI Agents SDK. Manage Homebase shifts and timecards with built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Homebase MCP to OpenAI Agents SDK

Create your Vinkius account to connect Homebase 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 Homebase with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Staffing With Guardrails

This MCP server gives your agent direct access to your Homebase scheduling data. You can build an agent that pulls staff availability from `get_employee_profile` and checks existing coverage with `list_scheduled_shifts` to fill open slots automatically. The OpenAI Agents SDK adds a critical layer of safety. It validates agent actions before they run, so you don't have to worry about a rogue agent making a mess of your schedule. It's workforce automation you can actually trust in production.

Monitor Your Workforce in Real Time

Get a live view of your operations. An agent can use `get_active_clock_ins` to see exactly who is on the clock right now, at any of your business sites. You can build alerts for when a location is understaffed or approaching overtime. Combine this with `list_timecards` to track actual hours against the plan. Since every action is logged in the OpenAI dashboard, you get a full audit trail of what data your agent accessed and when. No more guessing what your automation is doing.

Zero-Config Tool Discovery for Homebase

Connecting your agent is simple. Once you point the SDK at this MCP Server, it automatically discovers all the Homebase tools—no manual mapping required. Your agent immediately knows how to use `list_locations`, `list_employees`, and `list_departments`. This means you can get started right away. The agent understands the available actions and their parameters from the start, letting you focus on writing the business logic, not the boilerplate plumbing.

Setup guide

Set up Homebase 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 Homebase tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Homebase 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="Homebase Agent",
            instructions="You have access to Homebase 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 Homebase. 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 Homebase 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 Homebase MCP in OpenAI Agents SDK

First, install the SDK with pip. Then, create an `MCPServerStreamableHttp` instance pointing to your Vinkius endpoint URL. You pass that into the `Agent` constructor, and the tools are discovered automatically.

Yes. The first step is always to call `list_locations` to get the unique ID for each site. From there, your agent can loop through those IDs to run other tools like `list_scheduled_shifts` for each specific location.

Have your agent call `list_labor_budgets` to get the target numbers for a location. Then, use `list_timecards` to fetch the actual hours worked within a pay period. Your agent can then compare the two and flag any discrepancies.

It automates the data gathering. Your agent can pull all timecard data with `list_timecards` and cross-reference employee details using `get_employee_profile`. This gets you an accurate, pre-processed dataset ready for your payroll provider.

Your agent will handle employee profiles, shift schedules, and timecard data. The connection to the MCP server is secured by a single Vinkius token, and the server itself runs in an ephemeral sandbox. Plus, the OpenAI dashboard provides a full trace of every tool your agent uses, so you have a complete audit log.

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