How to Use the Magic Minutes MCP in Pydantic AI

Q: How do I register Magic Minutes MCP tools in Pydantic AI?

Install the slim package with MCP support. Initialize MCPToolset with your HTTP endpoint and pass it to your Agent. The framework automatically parses the tool schemas.

Q: Why should I use MCPToolset instead of MCPServerHTTP for the Magic Minutes MCP Server?

The MCPServerHTTP class is deprecated in the latest releases. MCPToolset provides a unified approach that handles both SSE and Streamable HTTP transports natively.

Enforce strict runtime typing on your meeting data with Pydantic AI and the Magic Minutes 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 Magic Minutes MCP to Pydantic AI

Create your Vinkius account to connect Magic Minutes 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 Magic Minutes with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe meeting retrieval via MCP Server

This server provides `get_meeting_details` and `get_meeting_minutes` to your Pydantic AI agents. Every response gets validated against your Pydantic models at runtime. If the API returns a string instead of an expected integer, the framework fails loudly. You never deal with silent data corruption. Your agent calls `list_meetings` and knows exactly what schema to expect. It works flawlessly whether you use OpenAI, Anthropic, or local models.

Validate task creation payloads instantly

Before your agent executes `create_task`, the framework ensures the payload matches your exact specifications. It pulls the necessary IDs using `list_tasks` and `get_task_details`. Missing fields trigger immediate validation errors. You connect the server using `MCPToolset` with the unified HTTP approach. Pass it to the agent's toolsets array. The older MCPServerHTTP method is deprecated, so stick to the modern implementation.

Navigate contacts and attendees securely

Your agent queries `list_meeting_attendees` and `list_contacts` to map out who was in the room. The data comes back structured and verified. You stop wasting cycles parsing messy JSON strings. You also run `check_api_health` to confirm the endpoint is alive before starting a long agent run. The integration supports Streamable HTTP and SSE transports. Your pipeline stays rigid, predictable, and correct.

Setup guide

Set up Magic Minutes 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": {
        "magic-minutes-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim package with MCP support. Initialize `MCPToolset` with your HTTP endpoint and pass it to your Agent. The framework automatically parses the tool schemas.

The framework throws a strict validation error immediately. Your agent refuses to proceed with hallucinated fields or malformed JSON payloads.

Yes. The framework is completely model-agnostic. You route the meeting tools through local LLMs just as easily as you would with hosted providers.

The `MCPServerHTTP` class is deprecated in the latest releases. `MCPToolset` provides a unified approach that handles both SSE and Streamable HTTP transports natively.

The server handles direct employee contact information and private action items. Vinkius executes these operations in an ephemeral, zero-trust container. No state persists after the runtime validation completes.

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