How to Use the Picktime MCP in Pydantic AI

Q: How do I set up the Picktime MCP Server with Pydantic AI?

Install the package with pip install "pydantic-ai-slimmcp" and initialize MCPToolset with your Vinkius HTTP URL. Pass the toolset directly to your Agent constructor to expose all ten scheduling tools.

Q: Can my Pydantic AI agent manage group events like yoga classes on Picktime?

Yes, your agent uses listclasses to fetch multi-attendee events. The framework validates the capacity limits and session details, ensuring the agent only books sessions with open slots.

Q: How do I filter bookings by date range using Pydantic AI?

Your agent calls listbookings with optional date filters to retrieve scheduled appointments. The framework validates the returned list, ensuring your agent receives clean booking objects.

Q: How does Vinkius secure Picktime payment status and customer notes?

Customer notes and payment statuses fetched via getbookingdetails are processed in ephemeral V8 isolates. Vinkius uses a single-token architecture to handle MCP authentication, keeping your sensitive transaction data isolated and secure.

Build bulletproof scheduling pipelines using Pydantic AI and the Picktime MCP Server to validate every API response at runtime.

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 Pydantic AI

Create your Vinkius account to connect Picktime to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe booking management with Pydantic AI

The `get_booking_details` tool returns critical customer contact info, booked services, and payment statuses that require strict validation. Pydantic AI checks this incoming payload against runtime schemas, forcing your agent to fail loudly if the data structure changes. This type-safe layer ensures that actions like `cancel_booking` are only executed when the payload matches your exact specifications. You avoid silent failures and corrupt calendar states when your agent updates active schedules using the MCP.

Validate real-time availability and service schemas

The `get_availability` tool fetches open time slots based on staff schedules and buffer times. Pydantic AI validates these slots immediately, ensuring your model never parses a malformed date or time string. Your agent combines this validation with `list_services` to verify prices, durations, and staff assignments before presenting them to users. This prevents your agent from hallucinatory pricing or booking non-existent services.

Structured multi-location and resource lookups

The `list_locations` tool returns addresses, timezones, and integrations for all business branches. Pydantic AI parses these fields into typed models, making it easy for your agent to route bookings to the correct location. When looking up resources, the agent calls `list_staff` to verify active status and roles. If a staff member's profile is missing required contact fields, the validation layer catches it before your model attempts to schedule a slot.

Setup guide

Set up Picktime MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "picktime-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Picktime tools.",
)

result = await agent.run("List recent Picktime transactions")
print(result.output)

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 Pydantic AI

Install the package with `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your Vinkius HTTP URL. Pass the toolset directly to your `Agent` constructor to expose all ten scheduling tools.

Pydantic AI raises a validation error at runtime instead of letting your agent proceed with bad data. This prevents issues like booking a service with an incorrect duration or an invalid location ID.

Yes, your agent uses `list_classes` to fetch multi-attendee events. The framework validates the capacity limits and session details, ensuring the agent only books sessions with open slots.

Your agent calls `list_bookings` with optional date filters to retrieve scheduled appointments. The framework validates the returned list, ensuring your agent receives clean booking objects.

Customer notes and payment statuses fetched via `get_booking_details` are processed in ephemeral V8 isolates. Vinkius uses a single-token architecture to handle MCP authentication, keeping your sensitive transaction data isolated and secure.

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