How to Use the Gumroad MCP in Google ADK

Q: Is the Gumroad MCP Server compatible with Google ADK?

Yes, you use the McpToolset class to register the server. It supports both Stdio and HTTP transports, making it easy to deploy within your existing Google Cloud infrastructure.

Q: How do I limit which Gumroad tools my Google ADK agent can use?

You can provide a toolnames filter when initializing the McpToolset. This prevents the agent from executing sensitive functions like createoffercode unless you explicitly authorize it.

Connect your Google ADK enterprise agents to Gumroad to automate sales workflows and data reporting.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gumroad MCP to Google ADK

Create your Vinkius account to connect Gumroad 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 Gumroad with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Gumroad integration for Google ADK agents

Your agents can now query your entire digital catalog using `list_products`. By integrating this MCP Server, your infrastructure gains direct visibility into your store's performance metrics. The server connects to your agent via `McpToolset`, allowing for seamless interaction with existing Google Cloud data pipelines. You can now bridge your ecommerce data with your broader enterprise reasoning tasks.

Targeted discount code generation

Generate unique offers programmatically using `create_offer_code` when your agent detects specific market conditions. It validates the request against your current catalog to ensure consistency. You control exactly which tools your agent can access by using a tool_names filter. This keeps your store operations secure while allowing the agent to act on your behalf.

Deep analysis of sales and subscriber trends

Leverage your agent's reasoning capacity to parse data from `list_sales` and `list_product_subscribers`. It identifies patterns that aren't obvious in standard reports. The long-context reasoning capabilities of your Gemini models allow the agent to synthesize this data over time. You get actionable insights without manual data extraction or spreadsheet work.

Setup guide

Set up Gumroad 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 Gumroad 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="Gumroad_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Gumroad 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 Gumroad. 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 Gumroad 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 Gumroad MCP in Google ADK

Yes, you use the `McpToolset` class to register the server. It supports both Stdio and HTTP transports, making it easy to deploy within your existing Google Cloud infrastructure.

You can provide a tool_names filter when initializing the `McpToolset`. This prevents the agent from executing sensitive functions like `create_offer_code` unless you explicitly authorize it.

The server does not persist your data; it acts as a pass-through for your agent's queries. Your Gumroad information exists only in memory during the execution of your agent's task.

While the server provides the data, you can easily pipe the results into your BigQuery tables. Your agent fetches the latest figures via `list_sales` and commits them to your database for long-term tracking.

You provide a single endpoint token to the server. This keeps your credentials secure and out of your agent code, ensuring that your Gumroad access remains controlled and private.

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