"Canonical" matching MCP servers:

Enables AI agents to audit a web page in one call — title, meta description, canonical, robots, Open Graph, headings, JSON-LD, security headers and page delivery — returning each finding with its evidence and a ready patch to apply. It also compares a deploy preview against production to surface only regressions, keeps audited pages in tabs with history and daily watches, and runs Lighthouse lab tests via PageSpeed Insights.

Exposes five tools that let an assistant list and inspect schema-mutation benchmark tasks, grade submitted JSON tool calls against canonical answers, run the benchmark against a chosen model, and read dataset provenance. It enables measuring whether a model follows the current tool schema or falls back on a memorized one.

Enables coding agents to coordinate local profilers, benchmark tools, trace processors, and direct command or artifact targets to produce bounded, typed runtime evidence about application, native, and GPU-kernel hotspots, including coverage, provenance, and limitations. It also supports optional durable preservation of native bytes and canonical evidence bundles by hash for later inspection and replay.