How to Use the Zoom MCP in Pydantic AI

Q: How do I ensure Zoom meeting creation is accurate using Pydantic AI?

You call createmeeting. Since every response validates against a schema, the agent won't proceed until it's certain the necessary data fields are present and correct.

Q: Can I manage Zoom webinars with Pydantic AI?

Yes. You use createwebinar to set them up, or listwebinars to see what’s already scheduled. The framework handles the necessary data types for these tools.

Q: What happens when I need to delete a Zoom meeting using Pydantic AI?

You use deletemeeting. Because of runtime validation, you know exactly when that deletion was confirmed and what resulting status code the API returned.

Q: Does the MCP Server support listing all users on Zoom with Pydantic AI?

Yup. Running listusers fetches user data, which is then immediately passed through Pydantic models for type-safe use by your agent.

Q: Which type of data does this server touch regarding Zoom users?

This MCP Server touches user configuration details when the agent interacts with tools like listusers or getuser.

Accurate Zoom management using the Pydantic AI framework for guaranteed correctness.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zoom MCP to Pydantic AI

Create your Vinkius account to connect Zoom 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 Zoom with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full lifecycle management of Zoom meetings.

You can start by listing all sessions with `list_meetings`. If you need to create one, use `create_meeting`. When the meeting is over, `delete_meeting` handles the cleanup. Because of Pydantic AI's validation, every step confirms success or fails loudly.

Handle all Zoom webinar workflows.

The framework supports managing webinars using `list_webinars` and `get_webinar`. You can also schedule brand new events with `create_webinar`. This ensures that every output structure is correct before your agent acts on it. It's built for reliability, guaranteeing the data shape you expect.

Manage user and meeting configurations.

To check who’s on Zoom, run `list_users`. You can get details with `get_user` or modify things using `update_meeting`. The Pydantic validation layer makes sure that the data returned from these calls is always usable.

Setup guide

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

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

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

You call `create_meeting`. Since every response validates against a schema, the agent won't proceed until it's certain the necessary data fields are present and correct.

Yes. You use `create_webinar` to set them up, or `list_webinars` to see what’s already scheduled. The framework handles the necessary data types for these tools.

You use `delete_meeting`. Because of runtime validation, you know exactly when that deletion was confirmed and what resulting status code the API returned.

Yup. Running `list_users` fetches user data, which is then immediately passed through Pydantic models for type-safe use by your agent.

This MCP Server touches `user configuration` details when the agent interacts with tools like `list_users` or `get_user`.

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