How to Use the Better Stack MCP in Google ADK

Q: How do I initialize Better Stack inside my Google ADK agent?

Install the package and pass the Vinkius HTTP URL to McpToolset. Then, pass that toolset directly to your LlmAgent tools array. Your Gemini model will immediately know how to use listmonitors and other tools over the MCP protocol.

Q: Can Google ADK map Better Stack incidents to BigQuery?

Yes. Your agent can call listincidents to get the latest alerts, then write that structured data directly into BigQuery. The long-context window allows the agent to process hundreds of incidents from getincident in a single run.

Q: How do I restrict Google ADK from deleting Better Stack monitors?

Use the toolnames filter when setting up McpToolset. You can omit deletemonitor entirely, ensuring the agent can only read state using listmonitors or getmonitor.

Feed Better Stack uptime data directly into your Google ADK enterprise agents for long-context incident analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Better Stack MCP to Google ADK

Create your Vinkius account to connect Better Stack 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 Better Stack with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise triage using Google ADK

Let your Gemini-powered agent pull active alerts using `list_incidents` and analyze them against historical data in BigQuery. The agent can ingest thousands of log lines in its 1M token context window to find the root cause of any `get_incident` payload. Once the agent determines the fix, it checks the schedule via `list_on_calls` to alert the right team. This keeps your Google Cloud infrastructure and external monitoring systems perfectly aligned.

Automated provisioning with Google ADK

Your enterprise agents can manage infrastructure checks dynamically. Use the `create_monitor` and `update_monitor` tools to register new endpoints as your Google Cloud deployment pipelines scale up. If you decommission an environment, the agent cleans up by calling `delete_monitor`. You can restrict which tools are exposed by configuring the tool_names filter during initialization.

Heartbeat and status page sync via MCP Server

Keep your public status pages accurate by letting your agent query `list_status_pages` and match it with internal service states. The agent checks background jobs using `list_heartbeats` to catch silent failures before users do. By exposing these tools through the MCP Server, your Google ADK agents can cross-reference external uptime with internal Vertex AI metrics, ensuring your operations team always has the full picture.

Setup guide

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

Install the package and pass the Vinkius HTTP URL to `McpToolset`. Then, pass that toolset directly to your `LlmAgent` tools array. Your Gemini model will immediately know how to use `list_monitors` and other tools over the MCP protocol.

Yes. Your agent can call `list_incidents` to get the latest alerts, then write that structured data directly into BigQuery. The long-context window allows the agent to process hundreds of incidents from `get_incident` in a single run.

Use the `tool_names` filter when setting up `McpToolset`. You can omit `delete_monitor` entirely, ensuring the agent can only read state using `list_monitors` or `get_monitor`.

Yes, this MCP Server integration supports both Stdio and HTTP transports. For production setups on Google Cloud, we recommend using the Vinkius managed HTTP endpoint to avoid running local node processes.

Your API tokens are stored securely in Vinkius, never exposed to Google ADK or Gemini. When the agent calls `list_heartbeats` or `get_monitor`, the request executes in an ephemeral sandbox that returns only the clean JSON payload.

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