How to Use the Ko-fi MCP in Google ADK

Q: How do I use the Ko-fi toolset with Google ADK?

You instantiate an McpToolset with the Vinkius server URL and pass it to your agent. The ADK handles the connection and makes the listtransactions tool available to your Gemini model.

Q: Can I filter Ko-fi transactions by date range with Google ADK?

The listtransactions tool itself just gets recent activity. For filtering, you'd have your Google ADK agent pull the data first, then process it in your Python code or load it into BigQuery for analysis.

Pipe Ko-fi transaction data directly into your Google ADK agents. Analyze income trends with Gemini and BigQuery.

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 Google ADK

Create your Vinkius account to connect Ko-fi to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Transaction Data to BigQuery

The `list_transactions` tool pulls your Ko-fi donation and sales history. Your Gemini-powered agent can fetch this data on a schedule. From there, the agent can write the results directly into a BigQuery table. This lets you build dashboards and run complex analytics on your creator income alongside other business data.

Long-Context Financial Summaries

Get your agent to pull months of data using `list_transactions`. The results can be fed straight into a Gemini model with a large context window. Ask your agent for high-level summaries, like 'What was my average monthly income from subscriptions in Q3?' or 'Identify my top 10 supporters by total donation amount.' The model can reason over the entire dataset at once.

Build Enterprise Agents with this MCP Server

This MCP Server provides a simple, reliable way to get financial data into your Google Cloud environment. It's a single tool, `list_transactions`, with a clear purpose. The Google ADK's `McpToolset` makes it trivial to add this capability. Your agent gets a new tool without you needing to manage API keys, hosting, or a separate data pipeline.

Setup guide

Set up Ko-fi MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Ko-fi tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Ko-fi_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Ko-fi tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You instantiate an `McpToolset` with the Vinkius server URL and pass it to your agent. The ADK handles the connection and makes the `list_transactions` tool available to your Gemini model.

The `list_transactions` tool itself just gets recent activity. For filtering, you'd have your Google ADK agent pull the data first, then process it in your Python code or load it into BigQuery for analysis.

Yes. Your connection to the Ko-fi MCP server is authenticated via a single Vinkius token. The server itself uses a read-only key for Ko-fi, so your agent can only view transactions.

Definitely. That's a core strength. Your agent can pull Ko-fi transactions, cross-reference them with customer data in a Google Sheet, and then use a Vertex AI tool to generate a forecast.

Your agent can only see Ko-fi transaction records, which include amounts, timestamps, and supporter details. The Vinkius platform isolates each request in a sandboxed environment, ensuring the agent can't access anything beyond the scope of the `list_transactions` tool.

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