How to Use the MoonClerk MCP in Google ADK

Q: Can I restrict which tools this MoonClerk MCP server exposes to my Google ADK agent?

Yes, you can pass a toolnames filter to the McpToolset instance. This lets you limit the agent to safe read tools like listplans while hiding more sensitive customer lookup endpoints.

Q: How does Gemini use MoonClerk data fetched via the MCP server inside the Google ADK?

Gemini reads the output of tools like listsubscriptions directly into its context window. Its long-context reasoning allows it to analyze hundreds of subscription records in a single turn.

Q: Can the agent detect failed payments?

Yes, the agent can call listpayments and filter the results for failed transaction statuses. It can then alert your team or trigger automated recovery workflows.

Track MoonClerk checkout metrics and customer plans using the Google ADK and Gemini long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MoonClerk MCP to Google ADK

Create your Vinkius account to connect MoonClerk 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 MoonClerk with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze checkout performance using Gemini

The `list_forms` tool on our MCP server gives your Google ADK agent direct access to all active hosted checkout templates. By feeding this structural data into Gemini's massive context window, the agent can compare active forms against transaction histories to find underperforming checkouts. You can combine this with BigQuery datasets using native GCP connectors. The agent queries your database for sign-up events, calls `get_form` to check the checkout configuration, and flags discrepancies in your conversion funnel.

Audit recurring subscriptions at scale

Your agent invokes `list_subscriptions` to extract active recurring agreements directly into your Google Cloud pipelines. The Google ADK structures this data so Gemini can run multi-step reasoning across thousands of subscriber records simultaneously. When an anomaly pops up, the agent triggers `get_subscription` to isolate the specific record. It then cross-references this with external ledger data stored in Google Cloud Storage to verify payment alignment.

Map payment records to enterprise data

The `list_payments` tool lets your Google ADK agent pull transaction histories to feed automated reconciliation pipelines. This eliminates manual exports by allowing the agent to fetch raw payload details directly. If a specific transaction needs closer inspection, the agent runs `get_payment` to pull the precise gateway status. The output can be written directly to your enterprise database using standard Google Cloud SDKs.

Setup guide

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

Pass the Vinkius HTTP URL to the McpToolset constructor during initialization. Your Google ADK agent will immediately gain access to tools like `list_customers` and `get_customer`.

Yes, you can pass a tool_names filter to the McpToolset instance. This lets you limit the agent to safe read tools like `list_plans` while hiding more sensitive customer lookup endpoints.

Gemini reads the output of tools like `list_subscriptions` directly into its context window. Its long-context reasoning allows it to analyze hundreds of subscription records in a single turn.

Yes, the agent can call `list_payments` and filter the results for failed transaction statuses. It can then alert your team or trigger automated recovery workflows.

Vinkius uses single-use ephemeral sandboxes to execute each tool call, meaning your customer records and subscription statuses are never cached. All traffic between Google Cloud and the API endpoint is fully encrypted in transit.

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