How to Use the Picktime MCP in OpenAI Agents SDK

Q: How do I connect Picktime to the OpenAI Agents SDK?

Install the SDK with pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass this instance in the mcpservers list when instantiating your agent to auto-discover all scheduling tools.

Q: Can my OpenAI Agents SDK assistant handle group sessions in Picktime?

Yes, your agent uses listclasses to fetch multi-attendee events like workshops or group training sessions. It checks capacity limits and handles bookings without exceeding the configured maximum attendee count.

Q: How does the OpenAI Agents SDK prevent double-booking on Picktime?

The agent calls getavailability to fetch real-time slots considering buffer times and current staff schedules. Because OpenAI's SDK enforces strict execution guardrails, the agent verifies the slot remains open before finalizing any action.

Q: What is the best way to handle multi-location scheduling with this SDK?

Use listlocations to resolve workspace boundaries before calling listservices or liststaff. This ensures your agent operates within the correct timezone and branch constraints.

Build production-ready scheduling agents with the OpenAI Agents SDK and Picktime MCP Server to handle customer bookings safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Picktime MCP to OpenAI Agents SDK

Create your Vinkius account to connect Picktime to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Picktime with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Safe booking changes with OpenAI Agents SDK

The Picktime MCP Server exposes `cancel_booking` directly to your agentic system so it can modify calendars without manual intervention. Your OpenAI agents use built-in guardrails to validate cancellation reasons before executing the change, preventing accidental schedule wipes. By combining `get_booking_details` with OpenAI's tracing dashboard, you monitor exactly why and when an agent canceled a slot. This setup ensures your production agent never drops a booking or acts on stale calendar data.

Real-time slot discovery and verification

The `get_availability` tool lets your agent find open slots for any Picktime service on demand. The OpenAI Agents SDK manages handoffs between a triage agent and a scheduling agent to match customer requests with actual openings. Your agents fetch location-specific rules using `get_location` and `list_locations` before presenting options to the user. This keeps your booking flows accurate across multiple physical branches without hardcoding timezone logic.

Automated staff and service matching

The `list_services` tool pulls durations, pricing, and staff assignments directly into your agent's context window. Your agent then queries `list_staff` to cross-reference employee availability before confirming a time. With the OpenAI Agents SDK, you can cache these tool definitions by setting `cacheToolsList=True` in your configuration. This keeps your latency low when agents parse group sessions via `list_classes` during high-traffic booking windows.

Setup guide

Set up Picktime 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 Picktime tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK with `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this instance in the `mcp_servers` list when instantiating your agent to auto-discover all scheduling tools.

Yes, your agent uses `list_classes` to fetch multi-attendee events like workshops or group training sessions. It checks capacity limits and handles bookings without exceeding the configured maximum attendee count.

The agent calls `get_availability` to fetch real-time slots considering buffer times and current staff schedules. Because OpenAI's SDK enforces strict execution guardrails, the agent verifies the slot remains open before finalizing any action.

Use `list_locations` to resolve workspace boundaries before calling `list_services` or `list_staff`. This ensures your agent operates within the correct timezone and branch constraints.

Your customer contact info and payment statuses processed via `get_booking_details` run inside ephemeral V8 isolates. Vinkius secures these MCP transactions with zero-trust architecture, meaning your customer names and notes are never stored or exposed to external networks.

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