How to Use the Cheddar MCP in Google ADK

Q: How do I configure the Cheddar MCP Server in Google ADK?

Install the framework via pip install google-adk. Create a StreamableHttpServerParameters object with your endpoint, wrap it in an McpToolset, and pass it to your LlmAgent constructor.

Give your Google ADK agents direct access to Cheddar billing data to merge subscription metrics with BigQuery analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cheddar MCP to Google ADK

Create your Vinkius account to connect Cheddar 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 Cheddar with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed billing history into Google ADK

Connecting the Cheddar MCP Server to Google ADK lets your Gemini models ingest entire billing histories using `list_cheddar_invoices`. Enterprise agents need massive context windows to spot churn patterns. The agent pulls the raw financial data and drops it directly into your Vertex AI pipelines. You filter the exposed capabilities using the `tool_names` parameter. If a reporting agent only needs read access, you restrict it to `list_cheddar_transactions` and `get_cheddar_product_info`. The model processes thousands of payment records at once thanks to Gemini's massive token capacity.

Merge subscription data with BigQuery

Your `LlmAgent` executes `get_cheddar_customer_details` to fetch current plan status, then cross-references that output against usage logs stored in Google Cloud. Analyzing revenue requires joining customer profiles with usage metrics. The MCP standard makes this cross-system querying trivial. The framework handles the HTTP transport automatically. You initialize the `McpToolset` with your Vinkius URL, and the agent starts pulling live subscription states. A scheduled job can identify at-risk accounts based on failed payments and trigger retention workflows.

Automated charge management at scale

Wrapping the `add_cheddar_charge` tool inside a Google ADK agent allows you to build automated remediation scripts. Manual billing adjustments slow down enterprise operations. When a customer upgrades via a chat interface, the agent applies the prorated charge instantly. Active promotions complicate these calculations. Before applying any fee, the agent checks `list_cheddar_promotions` to verify valid discount codes. You get precise, usage-based billing adjustments driven entirely by LLM reasoning.

Setup guide

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

Install the framework via `pip install google-adk`. Create a `StreamableHttpServerParameters` object with your endpoint, wrap it in an `McpToolset`, and pass it to your `LlmAgent` constructor.

You control exactly what the model can execute. Pass a list of specific strings to the `tool_names` filter on the toolset to expose `list_cheddar_customers` while blocking charge creation.

Gemini models handle long-context reasoning exceptionally well. Your agent can pull hundreds of records via `list_cheddar_transactions` and analyze the entire payload in a single pass without losing detail.

The framework natively connects these components. You extract customer pricing tiers using `list_cheddar_plans` and immediately route the structured output into your existing Google Cloud machine learning pipelines.

Vinkius routes your requests through ephemeral, isolated environments. When your agent fetches names and email addresses, the connection authenticates via a single endpoint token. The sandbox destroys itself the moment the data transfers back to your Google Cloud environment.

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