"Canonical" matching MCP servers:

Enterprise AI operator evaluation MCP server. 27 tools (22 read + 5 write) for measuring, benchmarking, diagnosing, and interv ening on how human operators use AI tools across 5 canonical metrics.

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.