How to Use the Google Lighthouse SEO Auditor MCP in Pydantic AI

Q: How do I install and configure the Google Lighthouse SEO Auditor with Pydantic AI?

Install pydantic-ai-slimmcp via pip. Then, initialize the unified MCPToolset with your Vinkius HTTP URL and pass it to your Agent's toolsets argument.

Q: Is the old MCPServerHTTP class still supported for this integration?

No, MCPServerHTTP is deprecated. You must use the unified MCPToolset class to connect your Pydantic AI agent to the Vinkius hosted MCP Server.

Get type-safe PageSpeed audits in Pydantic AI with runtime validation for every performance score.

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 Pydantic AI

Create your Vinkius account to connect Google Lighthouse SEO Auditor to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe SEO audits for Pydantic AI agents

Never worry about malformed audit payloads again. When your agent calls `run_lighthouse_audit`, the Pydantic AI integration validates the API response against strict Python schemas at runtime. If Google's API payload structure changes, your code catches the error immediately instead of failing silently. This strict validation keeps your automated pipelines clean. You get reliable, typed data structures containing your performance, SEO, and accessibility scores, ready for immediate use in your application logic.

Zero-fluff performance diagnostics you can trust

Most SEO tools return messy, unpredictable outputs that confuse LLMs. This MCP Server solves that by delivering structured JSON through the `run_lighthouse_audit` tool. Your agent receives clean lists of failed audits, like unoptimized images or render-blocking JS, with no extra noise. Because the data is structured, your agent can reliably parse the diagnostics. It can instantly generate the correct HTML or CSS modifications without guessing the field names or types.

Model-agnostic execution across any LLM backend

Pydantic AI doesn't lock you into a single model. You can run `run_lighthouse_audit` using OpenAI, Anthropic, Gemini, or even a local model. The framework handles the tool calling interface uniformly, so you can switch models without rewriting your audit logic. This flexibility lets you use fast, cheap models to trigger the audit, and then swap in a larger model only when you need deep code analysis to fix complex performance bottlenecks.

Setup guide

Set up Google Lighthouse SEO Auditor MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "google-lighthouse-seo-auditor-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Google Lighthouse SEO Auditor tools.",
)

result = await agent.run("List recent Google Lighthouse SEO Auditor transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]` via pip. Then, initialize the unified `MCPToolset` with your Vinkius HTTP URL and pass it to your Agent's `toolsets` argument.

The framework will raise a validation error instantly. Because Pydantic AI enforces runtime validation, your agent won't hallucinate fields or proceed with corrupt PageSpeed score data.

No, `MCPServerHTTP` is deprecated. You must use the unified `MCPToolset` class to connect your Pydantic AI agent to the Vinkius hosted MCP Server.

Yes. The framework fully supports async operations, allowing your agent to run multiple `run_lighthouse_audit` calls in parallel without blocking your main execution thread.

All HTTP requests run inside isolated V8 sandboxes. This MCP Server processes your target URLs and the resulting PageSpeed JSON data entirely in memory and immediately discards them, ensuring no data leaks occur.

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