No user-submitted related servers found.
Scored across 15 tools
Most tools have clearly distinct purposes, with the descriptions explicitly contrasting related operations like vivac_pop vs vivac_done, vivac_push vs vivac_add, and vivac_note vs vivac_add. Still, the dense conceptual overlap among close/suspend/save/add/decide/declare tools means a new agent could momentarily confuse a few boundaries. The descriptions resolve these well, but the set is not perfectly unambiguous at first glance.
Every tool uses the same vivac_ prefix followed by a single lowercase word, with no mixing of camelCase, snake_case, or inconsistent verb styles. Although not all names are verb_noun phrases, the convention is completely predictable across the set. The naming is consistent and readable.
With 15 tools, the server sits at the upper end of the ideal range but each tool maps to a distinct operation in the provenance-tree workflow. No tool feels redundant or trivial, and the count is well matched to the complexity of project memory, rules, decisions, and lifecycle management. The set is well-scoped.
The surface covers the core lifecycle: session briefing, search, reasoning inspection, open-item listing, rules, push/pop/done/park/save, and recording decisions, notes, commands, and declared judgments. Minor gaps remain, such as no obvious way to edit or delete an existing node's title, reason, or outcome, though the append-only design may make these intentional. Overall, agents have a robust workaround-compatible surface.