How to Use the Google Lighthouse SEO Auditor MCP in Google ADK

Q: How do I register the Google Lighthouse SEO Auditor with Google ADK?

You use the McpToolset class. Instantly connect by passing your Vinkius HTTP endpoint as the MCP Server parameter, then assign this toolset to your LlmAgent instance in your Python code.

Q: Can I limit which tools from the Google Lighthouse SEO Auditor are exposed to my Google ADK agent?

Yes, you can use the toolnames filter. If you only want the agent to have access to runlighthouseaudit and nothing else, simply pass that specific tool name in the toolset configuration.

Q: Can Gemini write code to fix the performance bottlenecks identified by the audit?

Absolutely. Once the agent gets the raw JSON from runlighthouseaudit, its long-context window allows it to compare the diagnostics against your actual codebase to suggest precise code changes.

Give your Gemini enterprise agents on Google ADK the power to run PageSpeed audits and fix technical debt.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Lighthouse SEO Auditor MCP to Google ADK

Create your Vinkius account to connect Google Lighthouse SEO Auditor 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 Google Lighthouse SEO Auditor with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run native PageSpeed audits inside Google ADK

Enterprise teams can now audit web performance at scale. Your Gemini agent uses the `run_lighthouse_audit` tool to check any public URL and pull concrete SEO metrics. Because it runs natively inside the Google ADK ecosystem, you can feed these results directly into Vertex AI models for deeper analysis. This MCP Server setup eliminates custom API integration code. You define the `McpToolset` in Python, and your agent immediately knows how to query the audit endpoint and interpret the performance data.

Connect SEO metrics to your BigQuery data lake

Raw audit data becomes far more valuable when paired with business metrics. Your agent can run `run_lighthouse_audit`, extract the Core Web Vitals, and write those scores directly to BigQuery. This lets you correlate page speed with actual conversion rates and user behavior. Since Gemini models support long contexts, you can pass years of historical performance data alongside new audit reports. The agent will pinpoint precisely when your site's performance began to decay.

Analyze complex enterprise sites with 1M+ token context

Large web properties generate massive audit logs. When your agent invokes the `run_lighthouse_audit` tool, the returned payload can be huge. This MCP integration handles this easily, allowing Gemini to analyze thousands of lines of diagnostics in a single reasoning step. The agent reads through every failed audit, from oversized images to slow server response times. It then drafts prioritized tickets for your engineering team, sorted by impact.

Setup guide

Set up Google Lighthouse SEO Auditor 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 Google Lighthouse SEO Auditor 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="Google Lighthouse SEO Auditor_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Google Lighthouse SEO Auditor 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 Google PageSpeed. 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 Google Lighthouse SEO Auditor 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 Google Lighthouse SEO Auditor MCP in Google ADK

You use the `McpToolset` class. Instantly connect by passing your Vinkius HTTP endpoint as the MCP Server parameter, then assign this toolset to your `LlmAgent` instance in your Python code.

Yes, you can use the `tool_names` filter. If you only want the agent to have access to `run_lighthouse_audit` and nothing else, simply pass that specific tool name in the toolset configuration.

Yes, it supports both. For cloud-hosted enterprise agents, the Streamable HTTP transport is ideal because it allows your serverless functions to connect to Vinkius over a secure web connection.

Absolutely. Once the agent gets the raw JSON from `run_lighthouse_audit`, its long-context window allows it to compare the diagnostics against your actual codebase to suggest precise code changes.

The URL inputs and returned PageSpeed scores are processed in a zero-trust sandbox. We do not log or store the audited URLs or the performance payloads, ensuring your enterprise site data remains 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