No user-submitted related servers found.
Scored across 9 tools
Most tools target distinct resources: resolve_system finds benchmarks, list_stigs enumerates them, finding_details and defense_details fetch text for specific ids, and install/check handle the knowledge base. The main overlap is between defenses_for_technique and techniques_for_actor, since the latter's include_defenses effectively re-runs the former's logic, and resolve_system vs list_stigs both deal with the benchmark catalog. The very detailed descriptions mitigate most of this, so an agent can usually pick correctly.
All names use snake_case consistently, with no casing chaos. The convention is only split between action-led names (resolve_system, list_stigs, search_techniques, check_sources, install_knowledge_base) and noun-phrase lookups (finding_details, defense_details, defenses_for_technique, techniques_for_actor), which reads a bit mixed but remains predictable and readable.
Nine tools is well within a healthy range and each appears to earn its place: a handful of query tools, two detail-fetch tools, and two knowledge-base lifecycle tools. Nothing feels redundant or thin.
The surface covers the full workflow: resolving systems, listing STIGs, fetching finding check/fix text, mapping techniques/actors to defenses and controls, fetching MITRE defense text, and installing/updating the knowledge base. A minor gap is a direct control-id lookup (controls are only reachable through technique/actor queries), but this is largely workable.