No user-submitted related servers found.
Scored across 31 tools
Most tools map to distinct resource+action pairs, but the set has real overlap: check_health, get_session_findings, and deep_check all serve diagnostic/quality purposes, with get_session_findings explicitly reusing check_health's detector, and recall/recall_with_context are near variants. The descriptions are thorough, but the boundaries are not crisp enough to guarantee an agent always picks the right one.
The dominant verb_noun snake_case pattern is consistent across get_*, list_*, delete_*, update_*, set_*, check_*, and *_memory/_episode families. Minor deviations exist: store and recall are bare verbs without objects, and persistence_status would fit the get_* family better as get_persistence_status.
At 31 tools the surface is heavy and exceeds the 25-tool threshold where a set starts to feel sprawling. Several clusters could be consolidated, notably the three persistence tools, the three diagnostic/health tools, and the export/import/merge trio, all of which are closely related.
Core lifecycle coverage is strong: memories, episodes, profiles, recall, import/export/merge, and health repair all have working read/write/delete paths. Minor gaps remain, such as no direct get_memory-by-id tool, no episode update operation, and a read-only operating context, but agents can work around these.