How to Use the Ko-fi MCP in Pydantic AI

Q: How does Pydantic AI ensure my Ko-fi data is correct?

Pydantic AI validates the JSON response from the listtransactions tool against a predefined Pydantic model. If the data doesn't match the expected schema—for example, a missing field—it raises an error instead of letting your agent use bad data.

Q: What happens if the Ko-fi API is down when my Pydantic AI agent calls it?

The MCPToolset will fail the HTTP request, and Pydantic AI will report an error. Your agent won't be left hanging or receive empty data; it gets a clear signal that the tool failed.

Q: Is this Ko-fi integration compatible with async in Pydantic AI?

Yes, the MCPToolset fully supports async operations. You can call listtransactions from within an async function without blocking your main application thread.

Get type-safe Ko-fi transaction data in your Pydantic AI agent. Stop worrying about silent API errors and data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ko-fi MCP to Pydantic AI

Create your Vinkius account to connect Ko-fi 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 Ko-fi with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteed Data Schemas

This server's `list_transactions` tool returns a list of your Ko-fi donations and sales. Pydantic AI automatically validates every field in the response. If Ko-fi ever changes their API or sends an unexpected null value, your code won't just fail silently. Pydantic AI will raise a `ValidationError` immediately, so you know exactly what went wrong and where.

Build Reliable Accounting Bots

Use `list_transactions` to build an agent that syncs your Ko-fi income to a database or spreadsheet. You get a structured, predictable data source. Because every response is parsed into a Pydantic model, you can trust the data types. No more defensive code checking if `amount` is a string or an integer — if it passes validation, it's correct.

A Model-Agnostic Ko-fi MCP Server

Pydantic AI doesn't care if you're using OpenAI, Gemini, or a local model. This MCP Server works the same way with all of them. Just add the `MCPToolset` to your agent. It will discover the `list_transactions` tool and handle the HTTP requests, letting you focus on what to do with the validated Ko-fi data.

Setup guide

Set up Ko-fi 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": {
        "ko-fi-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Ko-fi 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 Ko-fi. 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 Ko-fi 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 Ko-fi MCP in Pydantic AI

Pydantic AI validates the JSON response from the `list_transactions` tool against a predefined Pydantic model. If the data doesn't match the expected schema—for example, a missing field—it raises an error instead of letting your agent use bad data.

The model is defined by the MCP server to match the Ko-fi API. You can't change it, but you can be sure that any data you get from the tool will conform to that rigid structure.

The `MCPToolset` will fail the HTTP request, and Pydantic AI will report an error. Your agent won't be left hanging or receive empty data; it gets a clear signal that the tool failed.

Yes, the `MCPToolset` fully supports async operations. You can call `list_transactions` from within an async function without blocking your main application thread.

Only your Ko-fi transaction history is accessed, including details like donation amounts and timestamps. The connection is managed by Vinkius, which uses single-use, ephemeral environments for each request. Your Pydantic AI agent never handles raw credentials.

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