In-depth architectural comparison of the Standard Vocal MCP and Lobbyvoices MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Standard Vocal MCP
Conversational AI · Local stdio
Quality: 53/100 (Good) | Auth: No auth required
Lobbyvoices MCP
Conversational AI · Local stdio
Quality: 53/100 (Good) | Auth: No auth required
Verdict Summary: Choose Standard Vocal MCP if you need specialized Conversational AI tools running via a local process. Choose Lobbyvoices MCP if your workspace requires Conversational AI integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Standard Vocal MCP when:
You need dedicated capabilities in the Conversational AI domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Voice Agent Factory for Vapi phone agents: vertical templates, self-testing agents, audio forensics, prompt versioning, and CI regression gates. npx -y standard-vocal-mcp
Official remote MCP server for Lobby, an AI receptionist for small businesses. Seven free no-auth tools: write business phone scripts and IVR menus (English + Mexican Spanish), generate ElevenLabs agent system prompts, calculate missed-call cost, get a hire-a-receptionist verdict, role-play a call against the live receptionist engine, and get a real demo number to call. Typed structured outputs.
Category & Scope
Tools & Capabilities Breakdown
Standard Vocal MCP Tools (6)
list_agents
Lists the assistants on the account (id, name, model, voice, transcriber) — the entry point to find an `assistantId`.
deploy_agent
One tool = one full vertical deployment. `deploy_agent(vertical: elagueur\
run_eval
The agent tests itself.** Fetches the live system prompt, simulates N scripted scenarios against the configured LLM, scores behavior (close speed, no price quoting, spelled digit confirmation, urgency priority, solicitation refusal), returns a `/100` grade with PASS / WARN / FAIL. No audio, no bill…
audio_forensics
Downloads the 3 recording tracks of a call (mono / customer / assistant), runs RMS-per-window analysis, and **locates the noise source**. Automates the exact manual investigation that found a "computer noise" issue was injected downstream of the caller's mic, not in Vapi.
prompt_diff
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Standard Vocal MCP is categorized under Conversational AI and uses a local stdio subprocess. In contrast, Lobbyvoices MCP belongs to Conversational AI using local stdio subprocess. Select Standard Vocal MCP when you need capabilities focused on conversational ai and Lobbyvoices MCP when you require tools for conversational ai.
Generates a production-grade system prompt for an ElevenLabs conversational agent acting as a phone receptionist.
calculate_missed_call_cost
Computes the revenue a business loses to missed calls (monthly + yearly) plus recovery math, break-even days, and ROI.
simulate_receptionist_call
Role-play a call against the receptionist call engine — you play the caller, get the transcript, outcome, and automatic EN/ES switch back.
get_demo_call_number
A real phone number anyone can call right now to hear the receptionist live, with suggested bilingual scripts.
should_i_hire_a_receptionist
Scores a business's phone coverage and returns a verdict — covered, AI front desk, or hybrid — with archetype and leak numbers.
save_my_receptionist
Saves a phone script, IVR menu, agent prompt, or simulated call built earlier in the conversation and emails it to the person, with the demo number and a signup link. Requires their explicit consent — only fires with `consent: true`.