How to Use the Payfunnels MCP in Pydantic AI

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

Instantiate MCPToolset with your Vinkius HTTP URL and pass it to the toolsets list in your Agent constructor. Pydantic AI will automatically generate type-safe schemas for these MCP tools.

Q: Is the deprecated MCPServerHTTP class required for this setup?

No, you should use the unified MCPToolset class instead of the deprecated server classes. This unified approach supports both Streamable HTTP and SSE transports out of the box.

Build type-safe billing agents with Pydantic AI and Payfunnels to guarantee error-free payments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Payfunnels MCP to Pydantic AI

Create your Vinkius account to connect Payfunnels 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 Payfunnels with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe payment link generation

Guarantee that your billing agent never outputs a malformed checkout URL by enforcing runtime validation. When the agent calls `create_one_time_payment_link`, Pydantic AI checks the title and amount fields against strict schemas before sending the request. If the model attempts to pass an invalid currency code or a negative amount, the framework catches the error immediately. This prevents broken payment links from ever reaching your customer's inbox.

Validated subscription tracking via Pydantic AI

Track recurring revenue safely by validating raw API payloads from this MCP Server. The `list_subscriptions` tool returns active customer data that Pydantic AI parses into strongly-typed Python models. Your code can confidently access fields like renewal dates and plan IDs without worrying about missing dictionary keys. If the subscription schema changes, your system fails loudly and safely instead of corrupting downstream databases.

Error-proof refund workflows

Automate charge reversals without risking accidental double-refunds or incorrect amounts. The agent uses `get_payment_details` to pull the original transaction details and maps them to a validated Pydantic model. Once the transaction is validated, the agent executes `refund_payment` with the exact verified amount. This strict type-checking prevents LLM hallucinations from draining your merchant account.

Setup guide

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

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

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

Instantiate `MCPToolset` with your Vinkius HTTP URL and pass it to the `toolsets` list in your Agent constructor. Pydantic AI will automatically generate type-safe schemas for these MCP tools.

The framework will raise a validation error instantly rather than letting your agent process corrupt billing data. This ensures your subscription records and payment links remain accurate.

Yes, since Pydantic AI is model-agnostic, you can use local models or alternative APIs to run your billing agents. The framework validates the inputs for these MCP tools regardless of the LLM you choose.

No, you should use the unified `MCPToolset` class instead of the deprecated server classes. This unified approach supports both Streamable HTTP and SSE transports out of the box.

All subscription statuses, setup fees, and checkout links are validated in memory and never stored on disk. The Vinkius MCP sandbox ensures your API keys are kept secure and isolated from the LLM providers.

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