How to Use the Hexometer MCP in Google ADK

Q: Can I use this Hexometer integration to monitor a large number of sites?

Yes. The listmonitoredsites tool is designed for this. Your Gemini agent can fetch the full list and then decide which sites need a deep dive with tools like runseoaudit or checkspeedmobile.

Q: Can my agent check for specific technical errors on a page?

It can. The checkpageerrors tool scans a given URL for things like JavaScript errors or assets that are too large. The agent gets a structured list of issues it can then act on.

Connect Gemini to your site's vitals. Monitor Hexometer performance metrics using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hexometer MCP to Google ADK

Create your Vinkius account to connect Hexometer 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 Hexometer with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Long-Term Site Trends

Go beyond simple "is it up?" checks. With Gemini's massive context window, your agent can pull months of data from `get_uptime_stats`. It can hold all that history in its context to spot recurring patterns or performance degradation over time. You can correlate this data with your own business metrics. Have the agent pull Hexometer speed data via `check_speed_desktop` and compare it to conversion rates from a BigQuery table. This is the kind of analysis that's hard to do manually.

Integrate Monitoring into Google Cloud

This isn't just another dashboard. You're bringing Hexometer's tools directly into your GCP environment. Your agent, running on Vertex AI, can use `get_security_status` to check your site's SSL certificate and trigger a Cloud Function if it's about to expire. The setup is straightforward. You create a `McpToolset` pointing to this server. Your agent can then call tools like `list_recent_alerts` and pipe the output directly into Pub/Sub or log it to Cloud Logging for permanent records.

Build Enterprise SRE Agents with this MCP Server

Manage your entire web presence from one place. An agent can start with `list_monitored_sites` to get an inventory of all your properties. From there, it can systematically run `check_broken_links` and `check_page_errors` on each one. Since the Google ADK lets you filter tools, you can create focused agents. Give your marketing agent access only to `run_seo_audit`, while your SRE agent handles the uptime tools. This MCP server provides the raw capabilities for your agents to act on.

Setup guide

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

You just need the server URL from Vinkius. In your Python code, you create an `McpToolset` with that URL and pass it to your `LlmAgent`. The ADK handles the connection and tool calls.

Yes. The `list_monitored_sites` tool is designed for this. Your Gemini agent can fetch the full list and then decide which sites need a deep dive with tools like `run_seo_audit` or `check_speed_mobile`.

The main benefit is connecting Hexometer's real-time site data to your existing Google Cloud services. Your agent can reason over performance metrics from `check_speed_desktop` and data in BigQuery within the same session.

It can. The `check_page_errors` tool scans a given URL for things like JavaScript errors or assets that are too large. The agent gets a structured list of issues it can then act on.

Your connection is secured by a single Vinkius token. The MCP server processes requests ephemerally, meaning it doesn't hold onto your site URLs or the performance data from tools like `get_security_status`. It's a zero-trust pass-through.

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