SetLuca
Official# Luca for AI assistants
[Luca](https://setluca.com) helps coaches, creators, and experts manage the conversations that lead to sales. This connection lets you ask an AI assistant about your Luca workspace and get help with the work waiting there.
You can ask it to show what needs attention, find a lead's conversation before a call, draft a reply in your voice, or explain how a campaign is doing. It can also help plan your next campaign or follow up on calls that still need an outcome.
Your assistant must get your approval before it takes an action that reaches a lead, such as sending a message or launching a broadcast. Replies drafted by Luca still wait for your review in Luca.
## Get connected
Luca works with assistants such as Claude, ChatGPT, and Cursor. Some connect through your Luca sign-in. Others use an API key you create in Luca. The public [connection guide](https://setluca.com/connect) walks through both options and helps you choose the one your assistant supports.
Once connected, try asking:
- "What needs my attention in Luca this morning?"
- "Show me the review queue and recommend what to approve."
- "Pull up everything about this lead before my call."
- "Draft a short, warm reply for this lead."
- "How is my broadcast performing?"
If a connection stops working, check the steps in the connection guide. You can manage or revoke connected assistants in **Luca → Settings → Connected agents**. You can revoke an API key in **Luca → Settings → Developer API keys**.
## Your data and your choices
The assistant only sees what the Luca access you give it allows. This connection does not keep its own copy of your workspace data. It passes your requests to Luca and returns the results to your assistant. Review the privacy policy of any assistant you connect before sharing a live workspace with it.
Read [Luca's privacy policy](https://setluca.com/privacy) for details about how Luca handles your data.
## For people building with Luca
Start with the [documentation index](./docs/README.md). It points to setup, tool examples, the [privacy](./docs/privacy.md) and [security](./docs/security.md) guides, development instructions, tests, and release steps. [AGENTS.md](./AGENTS.md) gives coding agents a short checklist. The [changelog](./CHANGELOG.md) lists changes by version, including changes to tool names that may affect saved prompts.
You can browse the [Luca API docs](https://api.setluca.com/docs) if you want to build a direct integration.
TDQS
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.