How to Use the Aporia MCP in Google ADK

Q: Can I restrict which Aporia tools Google ADK sees?

Yes. You can use the toolnames filter in the MCP Server configuration to expose only specific endpoints, like just the guardrails.

Wire Aporia into Google ADK to enforce strict guardrails and monitor Gemini model drift across your enterprise data pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aporia MCP to Google ADK

Create your Vinkius account to connect Aporia 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 Aporia with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Active guardrails for Google ADK

The `validate_guardrails` tool scans LLM interactions for PII leaks, toxicity, and off-topic behavior. You feed it your message arrays, and it tells your Gemini agent if the output is safe to proceed. When you process massive 1M+ token contexts from BigQuery, hallucinations happen. This MCP Server catches those errors inline, forcing the agent to rethink its answer before writing bad data back to your cloud infrastructure.

Track Vertex AI model drift

The `get_metrics` tool fetches exact performance numbers for any model Aporia watches. You use `list_models` to find the specific deployment you want to inspect. Enterprise agents need to know when their underlying models degrade. Your agent pulls these metrics daily, logging drift statistics straight into your GCP monitoring stack.

Run safety monitors on demand

The `trigger_monitor` tool executes a specific Aporia monitor exactly when your agent needs it. You can check what is available by calling `list_monitors` and `list_dashboards`. Passive logging fails in autonomous systems. By triggering checks dynamically, your agent verifies its own reasoning steps against your safety rules during complex, multi-step operations.

Setup guide

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

Install google-adk and configure a McpToolset using StreamableHttpServerParameters. Pass that toolset directly to the tools argument of your LlmAgent.

Yes. You can use the tool_names filter in the MCP Server configuration to expose only specific endpoints, like just the guardrails.

It works with any model you use. The MCP Server validates the text output, completely independent of the underlying LLM architecture.

The tool returns a failure state. Your agent reads this result and triggers a fallback protocol, like refusing to answer or querying a different data source.

The server inspects the raw text strings and message histories you submit to the guardrail endpoints. It evaluates the text for PII or toxic markers in real time and discards the payload without persisting your proprietary enterprise data.

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