How to Use the MakePlans MCP in OpenAI Agents SDK

Q: How do I connect the MakePlans MCP Server to the OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp object with your server URL, then pass it as mcpservers=server to your Agent constructor inside an async context manager.

Q: Can the MakePlans agent check for double bookings?

Yes. The agent calls findavailableslots with a specific serviceid and date range. It reads the open times directly from the schedule before attempting to execute a new booking.

Q: Does the OpenAI Agents SDK cache the MakePlans tools?

It does. You pass cacheToolsList=True during setup. This prevents the SDK from re-fetching definitions for listcustomers and other endpoints on every single agent run.

Q: How do I handle new users in MakePlans with OpenAI Agents SDK?

Your agent detects an unknown user and calls createnewcustomer with their name. It takes the resulting person ID and immediately uses it to schedule their requested service.

Build production scheduling agents with OpenAI Agents SDK. Connect MakePlans to handle bookings while enforcing strict execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MakePlans MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-discover MakePlans MCP Server tools

Your OpenAI agent automatically discovers the `create_new_appointment` and `find_available_slots` tools when you pass the server to the constructor. You don't write custom integration code. The SDK reads the tool definitions directly from the server and exposes them to the LLM. Set `cacheToolsList=True` to cut down on initialization time. Once connected, your agent evaluates user requests, queries `list_available_services`, and books exact times without hallucinating parameters.

Enforce guardrails on customer data

The `create_new_customer` tool requires a name parameter before executing. OpenAI's built-in guardrails validate this input before the agent actually hits the MakePlans API. If the LLM tries to submit malformed data, the SDK blocks the action and forces a correction. Every interaction with `get_appointment_details` or `list_customers` logs directly to your OpenAI dashboard. You see exactly what the agent read from the scheduling database and why it made specific booking decisions.

Route booking tasks between specialized agents

The `list_booking_resources` tool feeds staff and room availability to your system. When a user asks for a complex multi-step reservation, a triage agent hands off the specific scheduling task to a dedicated MakePlans agent. This compartmentalizes your logic. The scheduling agent focuses entirely on executing `list_appointments` and managing the calendar, while other agents handle unrelated customer service tasks.

Setup guide

Set up MakePlans 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 MakePlans tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` object with your server URL, then pass it as `mcp_servers=[server]` to your Agent constructor inside an async context manager.

Yes. The agent calls `find_available_slots` with a specific `service_id` and date range. It reads the open times directly from the schedule before attempting to execute a new booking.

It does. You pass `cacheToolsList=True` during setup. This prevents the SDK from re-fetching definitions for `list_customers` and other endpoints on every single agent run.

Your agent detects an unknown user and calls `create_new_customer` with their name. It takes the resulting person ID and immediately uses it to schedule their requested service.

The server processes names via customer profiles and reads appointment timestamps. Vinkius runs this inside an ephemeral V8 Isolate Sandbox, so your endpoint token handles the auth and the container disappears immediately after the agent finishes its task.

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