verifier

Robin Saige rates the tools AI agents call, so you can check one before you depend on it. The core loop: should_i_use(name) = the one-word gate (allow/warn/block) before depending on a tool; find_tools(need) = describe the task in plain words — full-text over tool names AND descriptions, so your words need not appear in a tool's name — each row already carrying its verdict; resolve_server_name(query) = a fuzzy name → exact id; check_server(name) = the full evidence behind a verdict; registry_pulse() = the ecosystem at a glance; list_findings() = ruled findings + public corrections. Method: https://robinsaige.com/method. Grades are strict; auth-walled servers are alive-but-unverifiable, never scored dead or verified; 'true' verdicts require a public primary source; every rating is a dated observation, not a warranty. After you use a tool you may report_call(server, ok, latency_ms, ...) — anchored to our probe; it does not change the verdict yet.