How to Use the MagicBell MCP in Pydantic AI

Q: What happens if the MagicBell API changes and my Pydantic AI agent tries to use it?

Your agent will fail loudly with a ValidationError. Pydantic AI's runtime validation will detect the mismatch between the API response and your expected Pydantic model, preventing your application from processing incorrect data. This is a feature, not a bug.

Build type-safe agents with Pydantic AI that interact with MagicBell, ensuring every API response is validated against your models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MagicBell MCP to Pydantic AI

Create your Vinkius account to connect MagicBell 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 MagicBell with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Verifiably Correct Broadcast Data

The `get_broadcast` and `list_broadcasts` tools let your agent fetch notification data from MagicBell. You can check delivery status, review content, or build an internal dashboard. With Pydantic AI, the raw JSON response from the server is parsed and validated against a Pydantic model at runtime. If the API ever adds a field, changes a data type, or returns something unexpected, your code will raise a `ValidationError` immediately. No more silent data corruption.

Send Broadcasts with Confidence

Use the `create_broadcast` tool to trigger notifications from your Pydantic AI agent. It's a simple function call that connects your agent's logic to your users' devices. Pydantic AI also validates the input to the tool. This ensures your agent isn't trying to call `create_broadcast` with malformed data or missing arguments, catching bugs before the request even leaves your system.

A Model-Agnostic MCP Server Toolset

This MCP server provides a clean, typed interface to the MagicBell API. It's built to be consumed by agents that care about data integrity. Because Pydantic AI is model-agnostic, you can use this toolset with GPT-4, Claude, Gemini, or a local model. The validation happens in your code, giving you a consistent, reliable way to work with MagicBell regardless of the LLM you choose.

Setup guide

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

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

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

Your agent will fail loudly with a `ValidationError`. Pydantic AI's runtime validation will detect the mismatch between the API response and your expected Pydantic model, preventing your application from processing incorrect data. This is a feature, not a bug.

Define a Pydantic model for your notification structure. Have your agent use `create_broadcast`. Then, use a separate agent process with `list_broadcasts` to periodically verify that the broadcasts were created and match your models, creating a self-auditing system.

Yes. The MagicBell MCP server is completely independent of the LLM. As long as your local model can function-call, it can use the tools exposed by the server, and Pydantic AI will provide the type-safety layer on top.

There is a tiny, measurable overhead from Pydantic's data parsing and validation. For a service like MagicBell where the network call is the main bottleneck, this validation cost is negligible and well worth the correctness it guarantees.

The server processes notification content, which includes the title and body of your broadcast. Your data is handled in-memory within a secure Vinkius sandbox to process the request and is never persisted by the MCP server itself. The connection is always encrypted.

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