
frontdesklab
io.github.CloudCorpRecords/frontdesklab
Receptionist toolkit: phone scripts, IVR menus, voice-agent prompts, missed-call cost math.
Documentation
frontdesklab
Front-desk help for a small business, without hiring anyone first. frontdesklab is a local forwarding client for the hosted LobbyVoices receptionist toolkit: it answers tools/list on your own machine from the captured tool definitions and forwards every call to LobbyVoices, returning the answers exactly as the service sends them back.
With it you can draft the words a caller hears — a greeting, voicemail or on-hold script, a full press-one-for-sales IVR menu — in English, Spanish, or both. It can write the system prompt for a voice agent that answers as your receptionist, role-play a call so you can hear how the flow feels from the caller's side, and tell you the live demo number so you can ring the real thing. Two of the tools do arithmetic instead of writing: what missed calls are costing you each month, and whether your numbers say you should hire a receptionist, use an AI front desk, or go hybrid.
One captured tool is deliberately missing. The upstream surface also offers save_my_receptionist, which hands the vendor a person's business name and email address to save their details. That is lead capture, not receptionist tooling, so this rebuild does not serve it — it is absent from the tool list, rejected by the MCP layer, and not a CLI subcommand.
The tools
write_phone_script— A ready-to-record phone script: greeting, voicemail, on-hold message, or jingle lines, in English, Mexican Spanish, or both.businessis required;mode,trade,vibe,extraandlangsshape the result.write_ivr_menu— A complete IVR menu script with greeting, numbered options and an operator line, with sensible defaults per industry.businessis required;industry,options(up to 6),languageand a customgreetingare optional.generate_elevenlabs_agent_prompt— A production-grade system prompt for an ElevenLabs conversational agent working as a business receptionist.bizis required;agentName,industry,tasks,hours,spanishandtonerefine it.calculate_missed_call_cost— The monthly and yearly revenue lost to missed calls, plus recovery math, break-even days and ROI. All three figures are required:callsPerWeek,missedRatePct,avgJobValue.simulate_receptionist_call— A text-only role-play with the receptionist call engine, up to 6 caller lines, with automatic English/Spanish detection.callerSaysis required;businessdefaults to the demo business.get_demo_call_number— The live demo phone number anyone can call to talk to the AI receptionist, plus suggested things to say in English and Spanish. Takes no arguments.should_i_hire_a_receptionist— A verdict on your phone coverage — covered, AI front desk, or hybrid — with the yearly leak, suggested plan, break-even days and ROI.callsPerWeek,missedRatePctandavgJobValueare required;currentSetup,coverageNeededandspanishCallersrefine the score.
Install and run
As an MCP server via npm:
npx -y @reneturcios/frontdesklab mcp
MCP client configuration:
{
"mcpServers": {
"frontdesklab": {
"command": "npx",
"args": ["-y", "@reneturcios/frontdesklab", "mcp"]
}
}
}
As a container:
docker run -i ghcr.io/cloudcorprecords/frontdesklab
docker run --rm ghcr.io/cloudcorprecords/frontdesklab get_demo_call_number '{}'
CLI
One binary serves both the command line and the MCP server. Each tool is a subcommand taking a single JSON string with that tool's arguments:
frontdesklab write_phone_script '{"business":"Sunset Plumbing"}'
frontdesklab write_ivr_menu '{"business":"Sunset Plumbing","industry":"plumbing"}'
frontdesklab generate_elevenlabs_agent_prompt '{"biz":"Sunset Plumbing"}'
frontdesklab calculate_missed_call_cost '{"callsPerWeek":80,"missedRatePct":30,"avgJobValue":450}'
frontdesklab simulate_receptionist_call '{"callerSays":["Hi, I need a plumber tomorrow."]}'
frontdesklab get_demo_call_number '{}'
frontdesklab should_i_hire_a_receptionist '{"callsPerWeek":80,"missedRatePct":30,"avgJobValue":450}'
frontdesklab --version
Exit codes: 0 when the forwarded call succeeds, 1 when the upstream result is an error, and 2 for usage problems such as an unknown subcommand or a malformed JSON argument.
Configuration
LOBBYVOICES_MCP_URL— Overrides the upstream endpoint. The default is the pinned hosted endpoint,https://lobbyvoices.com/api/mcp. (The override variable is a reconstruction added by this rebuild.)
The LobbyVoices registry record declares no headers on its remote, so frontdesklab sends no authentication header of any kind — the calls are keyless.
Upstream failures — a JSON-RPC error from the service, a non-2xx response, an unreadable body, or a request that fails outright — are reported to the caller as an error result whose text starts with frontdesklab error:.
How forwarding works
The first forwarded call opens a session: an initialize request (protocol version 2025-03-26), followed by a notifications/initialized notification, then the tools/call itself. If the service answers the initialize request with an Mcp-Session-Id header, that value is carried on every later request, and the open session is reused for the rest of the process. Replies are accepted either as plain JSON or as server-sent events. Successful results pass through verbatim, including any isError flag and any extra fields the service includes.
Development
npm install
npm run build # tsc -> dist/ (dist/cli.js is the bin)
npm test # tsx --test test/*.test.ts — stubbed upstream, no network
npm run dev # run the CLI from source
The test suite checks the served tool list against the captured surface, asserts that save_my_receptionist is absent at registry, MCP and CLI level, exercises the session handshake and its reuse, asserts that no Authorization header is sent under any environment, and verifies that arguments go upstream untouched and results come back untouched.
License
MIT — see LICENSE. Copyright (c) 2026 Rene Turcios.
@reneturcios/frontdesklabnpm install @reneturcios/frontdesklabghcr.io/cloudcorprecords/frontdesklab:0.1.0docker pull ghcr.io/cloudcorprecords/frontdesklab:0.1.0:undefinedRelated Servers
io.github.CloudCorpRecords/abandoncheck
Judge whether a dependency is maintained, from factual signals: releases, commits, archival.
io.github.CloudCorpRecords/actionbridge
Zapier exposed actions as MCP tools via a generic action runner.
io.github.CloudCorpRecords/actionpin
GitHub Actions supply-chain hardener: audit workflows for unpinned actions and build a SHA pin plan.