How to Use the ChargeDesk MCP in Google ADK

Q: How do I configure ChargeDesk with Google ADK?

Import McpToolset from the ADK and pass your Vinkius URL into StreamableHttpServerParameters. Assign this toolset to your LlmAgent initialization. The agent will read the available billing tools automatically.

Q: Can Google ADK restrict which ChargeDesk tools the agent sees?

Yes, you use the toolnames filter when setting up the toolset. This prevents a read-only support agent from accessing the refund endpoint. You explicitly define which operations the agent is allowed to execute.

Q: How do I handle large customer lists with Gemini?

Call the listchargedeskcustomers tool and pass the JSON response directly into the prompt. Gemini's massive context window processes the entire customer list natively. You do not need to chunk the data or build a RAG pipeline.

Connect ChargeDesk to Google ADK to let Gemini agents manage billing records alongside your BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChargeDesk MCP to Google ADK

Create your Vinkius account to connect ChargeDesk 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 ChargeDesk with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Gateways with Google ADK

Query all your active payment processors at once using the `list_connected_gateways` tool. Gemini agents can cross-reference Stripe or PayPal status with your internal Google Cloud logs via this MCP connection. This setup catches routing errors before they cause failed transactions. Validating event endpoints is equally critical. Agents call `list_chargedesk_webhooks` to ensure your infrastructure is receiving payment updates. When a webhook fails, the agent writes the error directly to BigQuery for your data engineering team to investigate.

Cross-Reference Subscriptions in Long Context

Feed massive lists of recurring billing profiles into Gemini using the `list_chargedesk_subscriptions` tool. Because Gemini handles context windows over one million tokens, you dump thousands of subscription records straight into the prompt. The agent analyzes churn patterns without needing external vector databases. Individual transaction lookups happen through `get_charge_details`. The agent pulls the exact timestamp, fee breakdown, and gateway response for a specific payment. It then compares this raw ChargeDesk data against your Vertex AI models predicting customer lifetime value.

Execute Refunds via MCP Server

Reverse transactions securely by triggering the `refund_chargedesk_payment` tool. Your Gemini agent identifies a duplicate charge in the billing history and executes the refund across the correct gateway automatically. The action completes in seconds. Customer support agents need context before issuing those refunds. They run `get_customer_details` to check the user's total spend and dispute history. If the account is flagged in your internal systems, the agent denies the refund request and escalates to a human manager.

Setup guide

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

Import `McpToolset` from the ADK and pass your Vinkius URL into `StreamableHttpServerParameters`. Assign this toolset to your `LlmAgent` initialization. The agent will read the available billing tools automatically.

Yes, you use the `tool_names` filter when setting up the toolset. This prevents a read-only support agent from accessing the refund endpoint. You explicitly define which operations the agent is allowed to execute.

Call the `list_chargedesk_customers` tool and pass the JSON response directly into the prompt. Gemini's massive context window processes the entire customer list natively. You do not need to chunk the data or build a RAG pipeline.

The framework supports both Stdio and HTTP transports out of the box. Vinkius provides a managed HTTP endpoint, so you configure the agent to connect over the network. Local installation is completely unnecessary.

Vinkius routes your refund requests and charge amounts through an ephemeral execution layer. The MCP server exists only for the duration of the API call. We operate a zero-trust architecture that never logs your raw transaction payloads.

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