How to Use the Airbrake MCP in Google ADK

Q: How do I register the Airbrake MCP Server inside a Google ADK agent?

Run pip install google-adk and import McpToolset. Pass your Vinkius HTTP endpoint into StreamableHttpServerParameters and add the Airbrake toolset directly to your LlmAgent tool list.

Q: Can I restrict which Airbrake MCP tools my Google ADK agent can access?

Yes. You can pass a toolnames filter to the Google ADK McpToolset constructor. This lets you restrict your agent to read-only tools like listprojects while blocking write operations like reportnotice.

Connect your Google ADK enterprise agents to Airbrake to scan millions of tokens of error logs and system deploys.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airbrake MCP to Google ADK

Create your Vinkius account to connect Airbrake 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 Airbrake with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Airbrake error groups to BigQuery via Google ADK

Enterprise systems generate massive volumes of error telemetry that usually gets lost in static dashboards. With this MCP Server, your Gemini-powered Google ADK agents can call `list_error_groups` and cross-reference those errors with historical database logs stored in BigQuery. The Google ADK agent processes the combined data using Gemini's massive context window. It analyzes complex patterns across thousands of Airbrake incidents without hitting rate limits or losing track of the original stack trace.

Track Airbrake deploys with Google ADK and Vertex AI

Keep your enterprise cloud deployments stable by letting your Google ADK agents monitor system health. The agent runs `list_deploys` to check which code versions are live, then compares that against Vertex AI performance benchmarks to spot regressions. If a regression occurs, the Google ADK agent calls `track_deploy` to log the incident details directly back into your Airbrake dashboard. This creates a closed loop where your Vertex AI models and Airbrake monitoring tools share a single source of truth.

Map Airbrake projects across Google Cloud using Google ADK

Managing hundreds of microservices on Google Cloud is messy. This server lets your Google ADK agent use `list_projects` and `list_environments` to build a real-time topology of your active applications and their current health states. When a critical alert fires, the Google ADK agent queries `list_notices` to pinpoint which specific cloud environment is failing. You get immediate, contextualized Airbrake alerts inside your Google Cloud console instead of generic notification spam.

Setup guide

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

Run `pip install google-adk` and import `McpToolset`. Pass your Vinkius HTTP endpoint into `StreamableHttpServerParameters` and add the Airbrake toolset directly to your `LlmAgent` tool list.

Yes. You can pass a `tool_names` filter to the Google ADK `McpToolset` constructor. This lets you restrict your agent to read-only tools like `list_projects` while blocking write operations like `report_notice`.

Yes. While Vinkius hosts the Airbrake server over HTTP, the Google ADK framework natively supports both transport types, letting you switch configurations depending on your enterprise network rules.

Gemini's million-token context window inside Google ADK easily handles large outputs from `list_notices`. The model can ingest hundreds of raw Airbrake stack traces at once to find the root cause of a distributed system failure.

Your project configs and Airbrake environment tokens are encrypted in transit and processed inside an ephemeral MCP sandbox. Google ADK never persists your telemetry data, keeping your cloud logs completely private.

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