How to Use the Kiwify MCP in Pydantic AI

Q: Does Pydantic AI work with Kiwify subscriptions?

It does. Your agent calls listactivesubscriptions, and the toolset validates the response to ensure your subscription logic never encounters missing fields.

Q: Can I manage Kiwify webhooks using Pydantic AI?

Yes. You use listconfiguredwebhooks and createnotificationwebhook through your agent, maintaining strict schema enforcement for all operations.

Build type-safe Kiwify integrations with Pydantic AI to ensure every transaction record meets your strict schema requirements.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kiwify MCP to Pydantic AI

Create your Vinkius account to connect Kiwify 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 Kiwify with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-validated sales processing with Pydantic AI

Define your data models and let the framework enforce them at runtime. When your agent calls `list_sales_history`, the result is validated against your Pydantic schema immediately. If the API returns unexpected fields, the agent stops before processing bad data. Use `get_sale_details` to pull specific order info with full confidence in the types.

Subscription tracking with runtime safety

Monitor your recurring revenue while ensuring data integrity. The `list_active_subscriptions` tool brings in your subscriber list, which Pydantic AI validates against your defined model. This prevents silent errors in your billing logic. Your agent treats the data as trusted only after it passes the schema check.

Webhooks and account auditing

Manage your notification infrastructure with the same rigor you apply to your sales data. Use `list_configured_webhooks` to verify your current setup. When adding new endpoints via `create_notification_webhook`, define a schema that validates the response. This ensures your agent always knows exactly what it is talking to.

Setup guide

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

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

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

You define your Pydantic models in your agent code. When the MCP server returns data from `list_sales_history`, the framework automatically checks it against your types.

It does. Your agent calls `list_active_subscriptions`, and the toolset validates the response to ensure your subscription logic never encounters missing fields.

Yes. You use `list_configured_webhooks` and `create_notification_webhook` through your agent, maintaining strict schema enforcement for all operations.

You point the MCPToolset to your server endpoint with a token. This keeps your credentials out of your application code.

The server provides a direct, restricted link to your Kiwify account. Your agent only sees the transaction data you explicitly request through the validated tools.

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