Free receptionist building blocks: phone scripts, IVR menus in EN+ES, ElevenLabs agent prompts, and missed-call cost math.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 29 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The lobbyvoices MCP server exposes 8 tools, focused primarily on AI capabilities. Its published description reads: "Free receptionist building blocks: phone scripts, IVR menus in EN+ES, ElevenLabs agent prompts, and missed-call cost math". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates lobbyvoices F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Hidden instructions in a tool description" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check lobbyvoices's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add lobbyvoices to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://lobbyvoices.com/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
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.
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.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: generate_elevenlabs_agent_prompt
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
levenLabs agent system prompt Generates a production-grade system prompt forRecommendationRemove model-directed instructions from tool descriptions.
tool: save_my_receptionist
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
earlier in this conversation."},"notes":{"type":"string","description":"AnyRecommendationRemove side-channel parameters; constrain tool inputs.
tool: save_my_receptionist
A tool description tries to alter the model’s use of another tool.
ffer this after write_phone_script, write_ivr_menu, generate_elevenlabs_agent_promRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
tionist engine (simulate_receptionist_call), get the live demo phone number a human can caRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: write_phone_script
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "write_phone_script"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
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.
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.
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
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,
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.
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 lin