"author:tylerscomic-lab" matching MCP servers:

Scores MCP tool definitions and tool lists from 0-100, flagging vague descriptions, missing parameter docs, non-verb-first naming, oversized enums, and nested schemas with severity, rationale, and concrete fixes. It also validates marketplace listings against platform character caps such as MCPize's 500-character short-description limit before deploy.

Validates cron expressions and computes DST-correct next-fire times against real IANA timezone data, flagging schedules that silently skip a spring-forward run or double-fire on fall-back. Also surfaces the POSIX day-of-month/day-of-week OR semantics and other semantic footguns before a job ships.

Enables exact Claude API cost estimation from token counts with correct prompt-cache economics, plus cache break-even analysis showing whether and at which TTL reusing a prefix pays off. It also scans source code for tiktoken-based token counting used alongside Claude models and points to the correct fix.