How to Use the Cal.com MCP in Pydantic AI

Q: How do I integrate Cal.com with Pydantic AI?

Install pydantic-ai-slimmcp via pip. Create an MCPToolset pointing to your Vinkius HTTP endpoint and pass it as toolsets=toolset to your Agent. Avoid the deprecated MCPServerHTTP class.

Build type-safe scheduling agents with Pydantic AI and the Cal.com MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cal.com MCP to Pydantic AI

Create your Vinkius account to connect Cal.com to Pydantic AI 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 Cal.com with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type validation for Cal.com

Hallucinated calendar dates cause missed meetings when modifying schedules. Pydantic AI validates every response from `get_booking` against strict runtime models. If the API returns a string instead of a datetime object, your agent fails loudly with a validation error. Correctness beats speed when touching production databases. Triggering `cancel_booking` requires exact booking IDs. The framework ensures the LLM provides the correct data types before the request ever hits the network.

Type-safe event management via MCP Server

Managing meeting templates demands precision and strict type checking. When your bot calls `list_event_types`, the returned list maps directly to predefined Python schemas. You don't have to parse raw JSON dictionaries manually. Creating new formats uses the same rigorous checks. Executing `create_event_type` forces the agent to supply valid lengths and titles. Model-agnostic execution means this works perfectly whether you rely on OpenAI or a local Llama instance.

Read schedules without silent corruption

Availability data is notoriously complex to parse without a rigid schema. Calling `get_schedules` pulls raw time blocks, which the client immediately casts into verified objects. Developers receive clean, typed data every single time. User context dictates scheduling rules. The `get_current_user` tool returns timezones and default schedules, while `list_memberships` provides team context. Integrating these endpoints guarantees your agent respects organizational boundaries before proposing a time slot.

Setup guide

Set up Cal.com 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": {
        "calcom-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Cal.com 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 Cal.com. 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 Cal.com 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 Cal.com MCP in Pydantic AI

Install pydantic-ai-slim[mcp] via pip. Create an MCPToolset pointing to your Vinkius HTTP endpoint and pass it as toolsets=[toolset] to your Agent. Avoid the deprecated MCPServerHTTP class.

Yes, every single field gets checked at runtime. When you call `get_booking`, the framework ensures the response matches the expected schema. Any missing or malformed data triggers an immediate validation exception.

The framework is completely model-agnostic. You can pipe the `create_booking` tool into a local Ollama instance or Anthropic's Claude. The validation layer operates independently of the LLM provider.

You can connect using Streamable HTTP or Server-Sent Events (SSE). Since Vinkius hosts the external service, you just provide the connection URL. The underlying protocol handles the message framing automatically.

We never store your raw meeting templates or participant lists. The Vinkius zero-trust architecture processes the payload in an isolated environment. Once the `get_current_user` request finishes, the sandbox is destroyed completely.

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