How to Use the Hyperswitch MCP in Google ADK

Q: How do I initialize the Hyperswitch MCP server in your google-adk project?

Import McpToolset from the google-adk library and pass your Vinkius HTTP transport URL. Register this toolset inside your LlmAgent configuration to expose all payment and customer tools to Gemini.

Q: How do I restrict the google-adk tool exposure for the Hyperswitch MCP Server?

Use the toolnames filter when initializing your McpToolset in Python. You can restrict the agent to read-only tools like listcustomers and getrefund while blocking payout-related operations entirely.

Run Hyperswitch transactions and dispute resolution directly from your Google ADK pipeline using long-context Gemini models and MCP tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hyperswitch MCP to Google ADK

Create your Vinkius account to connect Hyperswitch 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 Hyperswitch with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reconcile BigQuery data with live Hyperswitch payments

Your Google ADK agent can query historical checkout trends in BigQuery and immediately cross-reference them with live transaction data. By invoking `list_payments` and `get_payment`, the agent identifies discrepancies between your data warehouse and actual processor states in real time. This makes financial reconciliation a breeze. The agent processes thousands of transactions in a single long-context window, flagging mismatched settlement statuses without requiring manual CSV exports.

Enterprise dispute analysis using Google ADK

Vertex AI excels at pattern recognition, and this integration puts that power to work on your chargebacks. Your Google ADK agent runs `list_disputes` to fetch active claims, feeding them into Gemini's massive context window to detect fraud rings. By calling `get_dispute` on flagged entries, the agent pulls granular transaction timelines. It compares these timelines against your enterprise risk models to predict which disputes are worth fighting.

Automated customer payout checks via MCP Server

Managing merchant payouts requires strict validation. This MCP Server lets your Google Cloud agent run `get_payout` and `list_payouts` to verify that funds are moving to the correct accounts. The agent matches the payout destination against verified enterprise profiles retrieved via `get_customer`. If any routing mismatch occurs, the agent halts the process and alerts your finance team via Google Cloud monitoring.

Setup guide

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

Import `McpToolset` from the `google-adk` library and pass your Vinkius HTTP transport URL. Register this toolset inside your `LlmAgent` configuration to expose all payment and customer tools to Gemini.

No, this toolset focuses on read and management operations. Your agent can query payment states using `get_payment` or list records via `list_refunds` to make decisions, but it cannot authorize new raw charges directly.

Use the `tool_names` filter when initializing your `McpToolset` in Python. You can restrict the agent to read-only tools like `list_customers` and `get_refund` while blocking payout-related operations entirely.

Yes, the tools return the exact currency and amount details provided by the underlying API. Your agent can read these fields from `get_payment` and compute conversions using your own financial logic.

All customer profiles and refund records are protected by Vinkius's zero-trust sandbox. The transit between Google Cloud and the payment router uses ephemeral, encrypted connections, ensuring raw PII never leaks into public training sets.

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