How to Use the Metronome MCP in Google ADK

Q: How do I connect the Metronome MCP Server to Google ADK?

Install google-adk and initialize McpToolset with your Vinkius HTTP endpoint. Pass this toolset into your LlmAgent configuration to give Gemini direct access to all 31 billing tools.

Q: Can Google ADK restrict which Metronome tools the agent can access?

Yes. You can pass a filtered list of tool names to the toolnames parameter in McpToolset to prevent the agent from calling sensitive tools like voidinvoice while allowing ingestion.

Feed BigQuery usage models directly into your billing pipeline with Google ADK and the Metronome MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metronome MCP to Google ADK

Create your Vinkius account to connect Metronome 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 Metronome with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery to Metronome MCP Server sync pipelines

The `ingest_events` tool takes raw usage data parsed from your BigQuery tables and pushes it to Metronome at rates up to 100,000 events per second. Your Gemini agent reads massive tables, identifies billing-relevant events, and batches them into this ingestion tool without manual pipelines. Using Google ADK, your agent runs these sync loops directly inside your Google Cloud environment. You don't need to write custom ETL scripts because the agent maps the BigQuery schema to the tool parameters on the fly.

Long-context contract analysis and creation

The `create_contract` tool lets your agent apply complex pricing agreements directly from scanned PDF contracts. Gemini's million-token context window reads the entire enterprise agreement, extracts the pricing tiers, and maps them to `create_rate_card` and `add_rate` calls. This setup removes the manual data entry step when onboarding massive enterprise accounts. The agent checks the existing catalog using `list_products` to ensure the correct base rates are applied before finalizing the contract.

Enterprise billing anomaly detection

The `get_usage_groups` tool pulls paginated, grouped usage data so your agent can scan for sudden consumption spikes. By comparing this real-time data against historical baselines in Vertex AI, the agent can immediately trigger `create_alert` to warn account managers. If an anomaly is confirmed, the agent can call `get_net_balance` to calculate the financial impact. This proactive monitoring keeps your customers from getting hit with unexpected overage bills at the end of the month.

Setup guide

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

Install `google-adk` and initialize `McpToolset` with your Vinkius HTTP endpoint. Pass this toolset into your `LlmAgent` configuration to give Gemini direct access to all 31 billing tools.

Yes. You can pass a filtered list of tool names to the `tool_names` parameter in `McpToolset` to prevent the agent from calling sensitive tools like `void_invoice` while allowing ingestion.

Gemini can analyze hundreds of pages of historical invoices and pricing agreements, then use `create_contract` to perfectly replicate those terms in Metronome without truncating the context.

Yes. When a threshold is crossed, your agent can catch the event, query `get_usage` to find the offending resource, and use this MCP toolset to query `create_notification` to alert the engineering team.

The MCP Server secures customer IDs, invoice records, and usage metrics by routing all API traffic through Vinkius's isolated V8 sandboxes. Your Metronome API tokens are injected securely at runtime, ensuring your Google Cloud environment never exposes production secrets to the LLM.

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