drio
Open app

PageSpeed MCP Server

Source

Pull pagespeed data using this MCP server.

Catalog onlyCatalog onlySTDIO

Overview

PageSpeed MCP Server is a Model Context Protocol server designed to enhance AI assistants' capabilities by enabling them to perform comprehensive web performance analysis using Google's PageSpeed Insights API.

To use the PageSpeed MCP Server, install it via Smithery or manually using npm, and integrate it with your AI assistant by configuring the settings in its configuration file.

  • Detailed performance metrics analysis including FCP, LCP, TTI, and CLS. - Best practices assessment and SEO analysis. - Accessibility audits to improve usability. - Robust error handling and customization options for analysis strategies.
  1. Analyzing website performance to identify bottlenecks.
  2. Evaluating accessibility to enhance user experience for all users.
  3. Performing SEO audits to improve site rankings on search engines.

Add to your AI client

Use these steps to connect PageSpeed MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "pagespeed-mcp-server-phialsbasement": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pagespeed-mcp-server-phialsbasement"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "pagespeed-mcp-server-phialsbasement": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pagespeed-mcp-server-phialsbasement"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "pagespeed-mcp-server-phialsbasement": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pagespeed-mcp-server-phialsbasement"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "pagespeed-mcp-server-phialsbasement": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pagespeed-mcp-server-phialsbasement"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pagespeed-mcp-server-phialsbasement": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pagespeed-mcp-server-phialsbasement"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "pagespeed-mcp-server-phialsbasement": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pagespeed-mcp-server-phialsbasement"
      ]
    }
  }
}

FAQ

What platforms are supported?

Windows, Linux, and macOS.

How do I handle errors during analysis?

The server includes robust error handling for common issues like invalid URLs and API rate limits.

Is there a way to customize the analysis?

Yes! You can provide additional parameters like analysis strategy and performance thresholds.

Research and data