Bring Scheduling Api
to Pydantic AI
Learn how to connect Timekit to Pydantic AI and start using 11 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Timekit MCP Server?
Connect your Timekit account to any AI agent and simplify how you manage resource availability, booking workflows, and customer appointments through natural conversation.
What you can do
- Resource Management — List all resources (people, rooms, equipment) and create new profiles to manage scheduling capacity.
- Booking Lifecycle — Create new bookings, confirm tentative requests, or decline/cancel existing appointments via AI.
- Availability Checking — Programmatically find available time slots for one or more resources based on specific date ranges and durations.
- Rescheduling — Easily move existing bookings to new time slots without manual dashboard entry.
- Workflow Control — Manage complex booking 'graphs' (instant, confirm_decline) directly from your workspace.
- Account Visibility — Retrieve detailed metadata for specific bookings and resources to stay on top of your schedule.
How it works
1. Subscribe to this server
2. Enter your Timekit API Key (found in your developer settings)
3. Start managing your scheduling infrastructure from Claude, Cursor, or any MCP client
Who is this for?
- Service Providers — quickly book client consultations and check availability via simple AI commands.
- Office Managers — manage room bookings and equipment scheduling across the organization directly from the workspace.
- Product Teams — automate the creation of resources and monitor booking flows via the AI assistant.
Built-in capabilities (11)
Cancel a confirmed booking
Check availability for resources
Confirm a pending booking
Create a new booking
Create a new resource
Decline a pending booking
Get details for a specific booking
Get details for a specific resource
List all bookings
List all resources (people, rooms, etc.)
Reschedule an existing booking
Why Pydantic AI?
Pydantic AI validates every Timekit tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Timekit integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Timekit connection logic from agent behavior for testable, maintainable code
Timekit in Pydantic AI
Timekit and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Timekit to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Timekit in Pydantic AI
The Timekit MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Timekit for Pydantic AI
Every tool call from Pydantic AI to the Timekit MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check availability for multiple resources at once?
Yes! Use the check_availability tool and provide a JSON array of Resource IDs. The agent will return time slots where all specified resources are available.
How do I confirm a tentative booking request?
Use the confirm_booking action and provide the unique Booking ID. This will transition the request from 'tentative' to 'confirmed' in your Timekit account.
Is it possible to reschedule an existing appointment via AI?
Absolutely. Use the reschedule_booking tool. Provide the Booking ID and the new start and end times to update the appointment instantly.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Timekit MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai