How to Use the Craft CMS (Craftnet) MCP in Pydantic AI

Build type-safe agents that manage Craft CMS (Craftnet) licenses and sales with runtime validation using 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 Craft CMS (Craftnet) MCP to Pydantic AI

Create your Vinkius account to connect Craft CMS (Craftnet) 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 Craft CMS (Craftnet) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Craftnet license schemas in Pydantic AI

Parse incoming JSON using `list_plugin_licenses` or `list_cms_licenses` to stop worrying about API payload drift breaking your production code. Pydantic AI evaluates the data against strict Python type models before your code does anything with it. If the Craftnet API adds a new field or changes a data type, the framework raises a validation error immediately. You catch schema drift in real-time instead of running into silent database corruption down the road.

Get type-safe sales and payout reports

Generate clean, structured data for tools like `list_sales_history` and `list_payout_history` to convert financial records into strongly typed Python objects. This MCP Server outputs validated models so Pydantic AI can handle them safely. Your agent can calculate net earnings or check transaction IDs knowing that every float, string, and timestamp matches your exact data models. No more parsing messy raw dictionaries or guessing if an ID is an integer or a UUID.

Query the Craft Store catalog with strict types

Fetch reliable metadata using `search_plugins_by_name` and `get_plugin_details` to feed verified schemas directly into your Pydantic AI agent. When your agent searches for extensions, it gets clean data every time. You can safely display plugin categories, developer names, and version numbers on your own site. The type-safety guarantees that empty or missing fields are caught and handled before they hit your frontend.

Setup guide

Set up Craft CMS (Craftnet) 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": {
        "craft-cms-craftnet-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Craft CMS (Craftnet) 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 Craftnet. 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 Craft CMS (Craftnet) 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 Craft CMS (Craftnet) MCP in Pydantic AI

This MCP Server returns structured JSON that Pydantic AI validates against its internal models. If the Craftnet API changes, the framework will fail loudly with a validation error, preventing corrupt data from entering your system.

Yes, Pydantic AI is completely model-agnostic. You can run a local model or any major cloud LLM to query `list_plugins` while keeping the exact same type-safety guarantees.

You pass your Vinkius credentials when creating the MCP connection. The framework handles the connection headers, allowing your agent to safely run tools like `get_account_details` without exposing raw API keys.

Pydantic AI will raise a validation error immediately. This keeps your financial calculations clean, as the model won't try to process incomplete transaction records.

All API requests run through Vinkius's zero-trust sandbox. When your Pydantic AI agent requests data using `list_craftnet_users` or `list_sales_history`, the transaction is processed in an isolated environment that deletes all memory of the call once the validated payload is sent back to your Python runtime.

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