No user-submitted related servers found.
Scored across 203 tools
There are effectively two overlapping layers: a granular raw-API surface (luca_review_queue_approve, luca_leads_draft, luca_cadences_pause, luca_bookings_outcome_record, luca_reports_morning) and an agent-friendly wrapper layer that re-implements the same actions (luca_approve_and_send, luca_draft_reply, luca_pause_cadence, luca_close_call_loop, luca_morning_report). An agent faces near-duplicate pairs like luca_leads_draft vs luca_draft_reply, luca_pause_cadence vs luca_cadences_pause, and luca_review_queue_list vs luca_triage_inbox with no clear rule for which to pick. Many individual domains (bookings, campaigns, review queue) also have adjacent tools whose boundaries blur.
The bulk of tools follow a clean luca_<resource>_<verb> pattern (luca_leads_list, luca_bookings_types_create, luca_campaigns_publish), but the wrapper/curated set breaks it with verb-first or noun-phrase names (luca_draft_reply, luca_approve_and_send, luca_book_call, luca_triage_inbox, luca_analytics_magic_monday). Everything is snake_case and readable, but the mixed verb styles across the two layers reduce predictability.
203 tools is an extreme mismatch for any single MCP surface, well beyond the 25+ range that already signals overload. The count is inflated by two parallel layers exposing the same operations plus many thin read-only analytics endpoints, making the set hard to navigate and select from.
Coverage is genuinely broad: leads, conversations, bookings (types, schedules, providers, outcomes), campaigns, broadcasts, webhooks, integrations, analytics, voice, memory, knowledge, and learning all have read plus create/update/delete operations. A few lifecycle actions are intentionally app-only (connecting channels, creating knowledge sources, CRM opt-in), which are reasonable gaps an agent can work around.