How to Use the Highnote MCP in Google ADK

Q: How do I connect the Highnote MCP server to my Google ADK agent?

You'll instantiate an McpToolset in your Python code, pointing it to your Vinkius server URL. Then you pass that toolset into your LlmAgent constructor. The agent will discover all 11 Highnote tools automatically.

Q: Can I filter which Highnote tools my Google ADK agent can use?

Yes. The McpToolset constructor in the Google ADK accepts an optional toolnames filter. You can provide a list of specific tool names, like gettransactiondetails, to restrict the agent's capabilities.

Q: Is it possible to use Highnote with Google ADK to reconcile ledger entries?

Absolutely. Your agent can use the listledgerentries tool to pull data from Highnote. It can then compare that data against records in a Google Sheet or BigQuery table to perform automated reconciliation.

Connect Google ADK agents to Highnote for real-time card issuance and financial analysis inside your Google Cloud environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Highnote MCP to Google ADK

Create your Vinkius account to connect Highnote 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 Highnote with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Finances, Analyze in BigQuery

Let your agent pull raw financial data directly from the source. It can fetch transaction lists with `list_financial_transactions` or get the fine-grained details needed for reconciliation using `list_ledger_entries`. Once the data is fetched, your agent can push it straight into a BigQuery table. This lets you run large-scale analysis on spending patterns from Highnote without ever leaving your Google Cloud project. It connects your agent's actions to your existing data warehouse.

Manage Your Card Program with a Gemini Agent

Give your Gemini-powered agent the tools to manage your entire card program. It can check available products with `list_card_products` and see all issued physical and virtual cards with `list_payment_cards`. When a customer has an issue, the agent finds their account with `list_account_holders` and pulls specific card details using `get_payment_card_details`. This MCP server gives your agent a direct line to your core financial operations on Highnote.

Act on Long-Context Financial Histories

Gemini's large context window means your agent can hold a customer's entire financial story at once. It can load a primary balance from `get_financial_account` and then pull all associated transactions with `list_financial_transactions`. The agent gets the full picture before acting. This avoids dozens of repetitive API calls and lets it make better decisions, like whether it's appropriate to use `update_card_status` to close an account.

Setup guide

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

You'll instantiate an `McpToolset` in your Python code, pointing it to your Vinkius server URL. Then you pass that toolset into your `LlmAgent` constructor. The agent will discover all 11 Highnote tools automatically.

Yes. The `McpToolset` constructor in the Google ADK accepts an optional `tool_names` filter. You can provide a list of specific tool names, like `get_transaction_details`, to restrict the agent's capabilities.

Absolutely. Your agent can use the `list_ledger_entries` tool to pull data from Highnote. It can then compare that data against records in a Google Sheet or BigQuery table to perform automated reconciliation.

Authentication is handled by the Vinkius platform. You pass a single endpoint token when configuring the `McpToolset`. The Google ADK doesn't need to store any separate credentials for Highnote.

Your Highnote data, like account holder names and financial account details, is processed within Google Cloud's secure infrastructure. Access is governed by your project's IAM policies, and the data itself passes through the Vinkius ephemeral sandbox, which isolates each request.

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