cwv-speed-engine
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | No | Python path used to run the MCP server from source. Set to 'src' to ensure the 'cwv_speed_engine' module is found. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cwv_audit_siteA | Run a comprehensive Core Web Vitals audit on a live URL or local HTML file, returning 0-100 score, LCP/CLS/INP metrics, and diagnostic findings. |
| cwv_optimize_htmlB | Transform and optimize HTML code with automated image dimensions, font preconnects, script deferral, and lazy loading to boost CWV scores. |
| cwv_generate_cache_configA | Generate immutable caching headers and security configuration files for Netlify, Vercel, Nginx, Next.js, Cloudflare, or Apache. |
| cwv_generate_pwaB | Generate W3C webmanifest, Service Worker (sw.js) caching bundle, and HTML header snippet for Progressive Web App compliance. |
| cwv_generate_og_cardA | Generate complete OpenGraph, Twitter Card meta tags, Schema.org JSON-LD, and SVG preview banner. |
| cwv_diff_performanceA | Compare two performance audits (URLs, files, or audit results) with score deltas and diagnostic comparison. |
| cwv_generate_speculation_rulesC | Generate W3C Speculation Rules () for instant zero-latency prerendering and 103 Early Hints. |
| cwv_audit_performance_budgetB | Audit web page assets against Core Web Vitals performance budgets (Scripts, Styles, Fonts, Images), simulate multi-network latency (3G/4G/5G), and generate standard Lighthouse budget.json. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct action (audit, generate, optimize, diff), but the two audit tools (cwv_audit_site and cwv_audit_performance_budget) share the 'audit' verb and could cause slight confusion, though descriptions clarify their different scopes.
All tools use a consistent cwv_ prefix and follow a clear verb_noun pattern (e.g., cwv_generate_speculation_rules, cwv_audit_site, cwv_diff_performance). No deviations in style.
Eight tools is an ideal count for a focused Core Web Vitals engine, covering auditing, generation, optimization, and comparison without bloat.
The surface covers key CWV workflows: site/budget audits, generation of caching, PWA, OG, and speculation rules, HTML optimization, and performance diffing. Minor gaps include explicit generation of resource hints like preload/prefetch or critical CSS, but core lifecycle is well-covered.