How to Use the Loop Subscriptions MCP in Pydantic AI

Q: How do I initialize the Loop Subscriptions toolset in Pydantic AI?

Use the MCPToolset class with your Vinkius HTTP endpoint. Pass the resulting toolset object into the toolsets list of your Pydantic AI Agent.

Q: Is the older MCPServerHTTP class still supported for this setup?

No, that class is deprecated. You should use the unified MCPToolset constructor to connect to your hosted server.

Build type-safe Shopify subscription agents using the Loop Subscriptions MCP Server and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Loop Subscriptions MCP to Pydantic AI

Create your Vinkius account to connect Loop Subscriptions 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 Loop Subscriptions with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe subscription management with Pydantic AI

This MCP Server exposes `get_subscription` to ensure that every Shopify API response is strictly validated against Pydantic models. Your Python type definitions are guaranteed to match fields like pricing, renewal dates, and status. If Shopify returns unexpected data formats, your application fails immediately instead of letting your agent hallucinate. Catching these anomalies early prevents corrupt state changes from affecting your customers.

Validate subscriber operations before execution

By using `pause_subscription` and `resume_subscription`, your agent modifies customer records with guaranteed schema alignment. The framework validates the arguments for `skip_next_order` before sending the payload to Shopify. Preventing runtime API errors keeps your automated scheduling logic completely reliable.

Safe customer auditing and reporting

This toolset exposes `list_customers` and `list_orders` with rigid schemas that your Python codebase can trust implicitly. Malformed payloads are blocked before they can trigger downstream parsing issues. You parse customer histories via `get_customer` to feed your downstream financial models. Every field is verified at the runtime boundary, keeping your accounting data clean.

Setup guide

Set up Loop Subscriptions 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": {
        "loop-subscriptions-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the `MCPToolset` class with your Vinkius HTTP endpoint. Pass the resulting toolset object into the `toolsets` list of your Pydantic AI `Agent`.

The framework will immediately raise a validation error at runtime. This prevents your agent from acting on corrupt or incomplete subscription data.

Yes, Pydantic AI is model-agnostic. You can connect this toolset to local models or commercial APIs while maintaining strict type safety.

No, that class is deprecated. You should use the unified `MCPToolset` constructor to connect to your hosted server.

Vinkius handles all authorization tokens externally, meaning your credentials are never exposed to the LLM. Only raw JSON payloads containing active subscription statuses, customer IDs, and order totals are transferred during active validation checks.

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