How to Use the Hotmart MCP in Pydantic AI

Q: Does this server work with the latest version of Pydantic AI?

Yes, it's designed to work with the MCPToolset class, which is the current, recommended approach. It supports the streamable HTTP transport for efficient data handling.

Connect Pydantic AI to Hotmart for type-safe, validated data. If the API returns junk, your agent will know instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hotmart MCP to Pydantic AI

Create your Vinkius account to connect Hotmart 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 Hotmart with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Data or Get an Error

This toolset lets your agent call `get_student_progress`. Pydantic AI then automatically validates the response against a strict data model before it ever hits your code. If the Hotmart API ever changes, or sends a string where you expect a number, you don't get silent data corruption. Your code gets a loud `ValidationError` so you can handle the problem immediately. It's about correctness, not guesswork.

Use Any Model, Keep Your Validation

You can use the `get_sales_history` tool with any LLM that Pydantic AI supports. It doesn't matter if it's OpenAI, a local model, or something else. The data validation happens in your Python environment, not the model. This means your agent's core logic is always protected from bad data, giving you the freedom to switch LLMs without rewriting your data handling code.

A Single, Clean Way to Connect your MCP Server

Setup is simple. You just use `MCPToolset("http://...")` to give your agent the full set of Hotmart tools. This one-liner is the modern, unified way to do it. It handles everything needed to call `list_products`, `list_subscriptions`, and all the other functions. You don't have to worry about transport protocols or deprecated classes; you just get the tools you need.

Setup guide

Set up Hotmart 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": {
        "hotmart-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

It doesn't guarantee the data is correct, it guarantees the *shape* of the data is correct. When your agent calls a tool like `get_student_progress`, Pydantic AI validates the response against a model. If a field is missing or has the wrong type, it raises an error.

Yes. Pydantic AI is model-agnostic. As long as you have a compatible local model configured, it can use the tools from this MCP server to interact with your Hotmart account.

The main benefit is reliability. You build your application logic on top of Pydantic models, which ensures that your agent is always working with clean, predictable data structures, protecting you from unexpected API changes.

Yes, it's designed to work with the `MCPToolset` class, which is the current, recommended approach. It supports the streamable HTTP transport for efficient data handling.

Pydantic AI itself just validates the structure of data like what's returned by `list_subscriptions`. Security is handled by Vinkius, which processes the request in an isolated environment and uses your single token for auth. The data, including subscription details, is never stored on our servers.

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