lobbyvoices-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| write_phone_scriptB | Writes a professional phone script for a business — greeting, voicemail message, on-hold message, or jingle lines — in English, Mexican Spanish, or both. Returns ready-to-record text. |
| write_ivr_menuA | Builds a complete IVR (phone menu / auto-attendant) script for a business: greeting, numbered options, optional Spanish-language switch, and the operator line. English, Spanish, or bilingual. |
| generate_elevenlabs_agent_promptB | Generates a production-grade system prompt for an ElevenLabs conversational agent acting as a business phone receptionist: identity, job, voice style, booking flow, guardrails, and escalation rules. |
| calculate_missed_call_costA | Computes the revenue a business loses to missed phone calls (monthly and yearly), plus the recovery math: recoverable revenue, suggested answering plan, break-even days, and ROI multiple. |
| simulate_receptionist_callA | Role-play a phone call with Lobby's receptionist call engine — the same pipeline behind the product demo: greeting, booking flow, lead capture, and automatic English/Spanish detection (live calls add a full AI brain on top). You play the caller: pass each thing the caller says, get the full transcript and outcome back. Free, text-only, max 6 caller lines. |
| get_demo_call_numberA | Returns a real phone number anyone can call right now to talk to Lobby's AI receptionist live — plus suggested things to say (English and Spanish) and what to listen for (the mid-call language switch, booking flow). |
| should_i_hire_a_receptionistB | Scores a business's phone coverage and returns a verdict — you're covered, get an AI front desk, or go hybrid — with the caller archetype, yearly leak, suggested plan, break-even days, and ROI. |
| save_my_receptionistA | Saves the phone script, IVR menu, agent prompt, or simulated call you just built for a real business, and emails it to the person you're helping — with the live demo number to hear it and a signup link to turn it on for real. Offer this after write_phone_script, write_ivr_menu, generate_elevenlabs_agent_prompt, or simulate_receptionist_call, once the human seems to want to keep the result or try it live. Requires the person's explicit consent to be emailed — ask first, and only call this with consent: true if they say yes. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Tools are mostly distinct with clear purposes, though write_phone_script and write_ivr_menu both involve script writing, and generate_elevenlabs_agent_prompt overlaps slightly with writing textual prompts. However, each targets a specific aspect of the receptionist workflow.
Most tools follow a verb_noun pattern (calculate_, generate_, etc.), but 'should_i_hire_a_receptionist' breaks the pattern with a full question, and 'save_my_receptionist' uses an informal style. Overall consistent with minor deviations.
8 tools is well-scoped for the domain of AI phone receptionists, covering analysis, creation, testing, and saving without being overwhelming or sparse.
The set covers the full lifecycle: decision support, script writing, prompt generation, simulation, and saving. Minor gaps like a tool to list existing saved scripts or edit them are absent, but core workflows are complete.