Performance AI MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/csoai-org-performance-ai-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

4 read · 0 write · 0 deleteRead-only

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• analyze_waterfall_data

  Analyze a resource loading waterfall for performance bottlenecks. Args: resources: List of resource dicts with keys: url, type (js/css/img/font/html/other), size_kb, start_ms, duration_ms, blocking (bool, optional) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis …

• calculate_core_web_vitals

  Calculate and rate Core Web Vitals scores. Args: lcp_ms: Largest Contentful Paint in milliseconds fid_ms: First Input Delay in milliseconds cls: Cumulative Layout Shift score inp_ms: Interaction to Next Paint in ms (optional, new metric) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool…

• image_optimization_hints

  Analyze images and suggest optimization strategies. Args: images: List of image dicts with keys: url (or name), format (jpg/png/gif/webp/svg), size_kb, width, height, above_fold (bool, optional) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification …

• suggest_optimizations

  Suggest performance optimizations based on page characteristics. Args: page_data: Dict with optional keys: total_size_kb, js_count, css_count, image_count, font_count, uses_http2 (bool), has_service_worker (bool), has_lazy_loading (bool), ttfb_ms, lcp_ms, cls, fid_ms Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use:…

Signals

Stars

0

Forks

0

Open issues

0

Weekly downloads

53

Last commit

Sep 4, 2026 (1 month ago)

Last release

Aug 19, 2026 (2 months ago)

Last package publish

Jun 13, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.CSOAI-ORG/performance-ai-mcp

Version

1.0.8

Auth

No auth

Packages

pypi performance-ai-mcp

License

MIT

Repository

github.com/CSOAI-ORG/performance-ai-mcp

First seen

Oct 24, 2026

Last checked

Oct 25, 2026

Source

Official MCP Registrygithub-graphql