How to Use the Metaplane MCP in Google ADK

Q: How do I register Metaplane tools in Google ADK?

Instantiate McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent. Your Gemini model immediately gains access to MCP tools like listmonitors and listincidents.

Q: Does Google ADK support all Metaplane MCP Server endpoints?

Yes. The MCP Server exposes all 10 tools, including listconfiguredalerts and getmonitorruns. You can filter the toolset if you want to restrict specific actions.

Q: How do I handle large database schemas with this toolset?

The listconnectionschemas tool returns structured metadata that fits easily into Gemini's large context window. This allows your agent to analyze complex warehouse relationships without running out of tokens.

Feed Metaplane data quality metrics directly into your Google ADK pipelines to protect your BigQuery tables.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metaplane MCP to Google ADK

Create your Vinkius account to connect Metaplane 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 Metaplane with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map BigQuery schemas inside Google ADK

The `list_connection_schemas` tool provides your Gemini agent with real-time structural data about your warehouse tables. When a query fails, the agent uses this tool alongside `list_data_connections` to trace schema changes back to the source. This MCP Server bridges the gap between your Google Cloud infrastructure and active data monitoring. Your agent reads the live warehouse state, avoiding outdated documentation and static config files.

Real-time anomaly tracking

The `list_incidents` tool feeds active data quality alerts directly into your Gemini long-context window. The agent calls `get_incident` to analyze the root cause of an anomaly, matching it against historical logs. Because Google ADK handles massive context, your agent can process multiple incident profiles simultaneously. It compares current failures with past runs to find recurring patterns without manual intervention.

Run tests on demand

The `trigger_monitor_run` tool initiates instant quality checks on your tables right after your ETL pipelines complete. Your agent tracks the progress using `get_monitor_runs` to ensure no corrupted rows leak into your production datasets. This active verification step stops bad data before it reaches your BI dashboards. Your agent monitors the run, inspects failures with `get_monitor`, and alerts the engineering team if thresholds are breached.

Setup guide

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

Instantiate `McpToolset` with your Vinkius HTTP URL and pass it to your `LlmAgent`. Your Gemini model immediately gains access to MCP tools like `list_monitors` and `list_incidents`.

While the agent cannot edit your database directly, it can use `get_incident` to pinpoint the broken table. It can then trigger a clean rebuild or alert your team before downstream jobs run.

Yes. The MCP Server exposes all 10 tools, including `list_configured_alerts` and `get_monitor_runs`. You can filter the toolset if you want to restrict specific actions.

The `list_connection_schemas` tool returns structured metadata that fits easily into Gemini's large context window. This allows your agent to analyze complex warehouse relationships without running out of tokens.

Your credentials and schema metadata reside in Vinkius's secure, ephemeral V8 sandboxes. Your Google ADK agent never handles raw database passwords, only interacting with the vetted MCP endpoint.

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