In-depth architectural comparison of the PageSpeed Insights MCP and Hub MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
PageSpeed Insights MCP
Developer Tools · Local stdio
Quality: 45/100 (Fair) | Auth: No auth required
Hub MCP
Developer Tools · Remote HTTP/SSE
Quality: 77/100 (Great) | Auth: API Key required
Verdict Summary: Choose PageSpeed Insights MCP if you need specialized Developer Tools tools running via a local process. Choose Hub MCP if your workspace requires Developer Tools integration with remote web transport. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose PageSpeed Insights MCP when:
You need dedicated capabilities in the Developer Tools domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
One run is noise, so this reports the median of several distinct PageSpeed analyses and the spread.
Official MCP server to interact with Docker Hub, providing access to repositories, hub search and Docker Hardened Images
Category & Scope
Tools & Capabilities Breakdown
PageSpeed Insights MCP Tools (8)
report
Everything in one call, and the one most people want. Scores with their spread, real-user data if Google has any, and what is failing ranked by what fixing it is worth. Returns a self-contained HTML page as well, to save or forward. Comes back as a job id.
check_pagespeed
Scores only. Median of N distinct analyses with the spread. `urls`, `strategy` (mobile, desktop or both), `runs` (1-10, default 5). Anything past a single analysis comes back as a job id.
diagnose_page
What is failing, ranked. Only reports a fault that failed in every analysis, because audits are as noisy as scores. Comes back as a job id.
field_data
Real-user data from the Chrome UX Report. `urls`, and `history` for the weekly p75 series.
explain_lcp
Which of four phases owns a slow Largest Contentful Paint: server response, the wait before the browser starts fetching the largest image, the download, then the wait before it is painted. One call, answers at once.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
PageSpeed Insights MCP is categorized under Developer Tools and uses a local stdio subprocess. In contrast, Hub MCP belongs to Developer Tools using remote streaming HTTP/SSE transport. Select PageSpeed Insights MCP when you need capabilities focused on developer tools and Hub MCP when you require tools for developer tools.
Did the change actually help. Measures now and compares against a saved baseline, giving a verdict only where the two ranges do not overlap. Comes back as a job id.
check_status
Collects a measurement that was handed back as a job id. Answers immediately, every time. `job_id`, or nothing at all for the most recent one.
diagnose
Whether the key works, whether the Chrome UX Report is reachable, and which baselines are held, without disclosing the key.
Hub MCP Tools (35)
search
Search repositories and content using Search V4 API
query
Search query parameter (string, required)
architectures
Filter on architectures (string, optional)
badges
Filter by image content type badges (string, optional)
categories
Filter on categories (string, optional)
extension_reviewed
Filter on reviewed extensions (boolean, optional)
from
Number of documents to skip for pagination (number, optional)
images
Filter on image names (string, optional)
operating_systems
Filter on operating systems (string, optional)
order
Change the ordering of results (string, optional)
size
Maximum number of results to return (number, optional)