MCP Integration

MCP Integration

Overview

Claude SEO can integrate with Model Context Protocol (MCP) servers to access external APIs and enhance analysis capabilities.

Available Integrations

PageSpeed Insights API

Use Google's PageSpeed Insights API directly for real Core Web Vitals data.

Configuration:

1. Get an API key from Google Cloud Console
2. Enable the PageSpeed Insights API
3. Use in your analysis:

curl "https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url=URL&key=YOUR_API_KEY"

Google Search Console

For organic search data, use the mcp-server-gsc MCP server by ahonn. Provides search performance data, URL inspection, and sitemap management.

Configuration:

{
  "mcpServers": {
    "google-search-console": {
      "command": "npx",
      "args": ["-y", "mcp-server-gsc"],
      "env": {
        "GOOGLE_CREDENTIALS_PATH": "/path/to/credentials.json"
      }
    }
  }
}

PageSpeed Insights MCP Server

Use mcp-server-pagespeed by enemyrr for Lighthouse audits, CWV metrics, and performance scoring via MCP.

Configuration:

{
  "mcpServers": {
    "pagespeed": {
      "command": "npx",
      "args": ["-y", "mcp-server-pagespeed"],
      "env": {
        "PAGESPEED_API_KEY": "your-api-key"
      }
    }
  }
}

Official SEO MCP Servers (2025-2026)

The MCP ecosystem for SEO has matured significantly. These are production-ready integrations:

API Usage Examples

PageSpeed Insights

import requests

def get_pagespeed_data(url: str, api_key: str) -> dict:
    """Fetch PageSpeed Insights data for a URL."""
    endpoint = "https://www.googleapis.com/pagespeedonline/v5/runPagespeed"
    params = {
        "url": url,
        "key": api_key,
        "strategy": "mobile",  # or "desktop"
        "category": ["performance", "accessibility", "best-practices", "seo"]
    }
    response = requests.get(endpoint, params=params)
    return response.json()

Core Web Vitals from CrUX

def get_crux_data(url: str, api_key: str) -> dict:
    """Fetch Chrome UX Report data for a URL."""
    endpoint = "https://chromeuxreport.googleapis.com/v1/records:queryRecord"
    payload = {
        "url": url,
        "formFactor": "PHONE"  # or "DESKTOP"
    }
    headers = {"Content-Type": "application/json"}
    params = {"key": api_key}
    response = requests.post(endpoint, json=payload, headers=headers, params=params)
    return response.json()

Metrics Available

From PageSpeed Insights

From CrUX (Field Data)

Best Practices

1. Rate Limiting: Respect API quotas (typically 25k requests/day for PageSpeed)
2. Caching: Cache results to avoid redundant API calls
3. Field vs Lab: Prioritize field data (CrUX) for ranking signals
4. Error Handling: Handle API errors gracefully

Without API Keys

If you don't have API keys, Claude SEO can still:

1. Analyze HTML source for potential issues
2. Identify common performance problems
3. Check for render-blocking resources
4. Evaluate image optimization opportunities
5. Detect JavaScript-heavy implementations

The analysis will note that actual Core Web Vitals measurements require field data from real users.