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
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Standard Vocal MCP.
list_agentsLists the assistants on the account (id, name, model, voice, transcriber) β the entry point to find an `assistantId`.
deploy_agentOne tool = one full vertical deployment. `deploy_agent(vertical: elagueur\
run_evalThe 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 billβ¦
audio_forensicsDownloads 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_diffPrompts as code. `snapshot` captures the live prompt into local history, `diff` compares two versions, `rollback` pushes an old prompt back to Vapi.
regression_gateCI for prompts.** Runs `run_eval` and blocks the update if the score regressed vs the stored baseline. Returns allow/deny with the reason.
A Voice Agent Factory exposed over the Model Context Protocol. Not a CRUD wrapper β a factory that deploys production phone agents, tests them, audits their audio, and gates their prompts like code.
Built on top of Vapi (telephony + LLM + STT + TTS). Differs from the official vapi-mcp-server, which is a generic CRUD wrapper over the Vapi API. This is the factory layer: vertical templates, self-testing agents, audio forensics, prompt versioning, CI regression gates.
The official Vapi MCP is 20 tools that each map to one raw API call. Anyone can read the docs and rebuild it in an hour.
This one encodes months of empirical tuning into its templates β transcriber parameters (numerals, confidenceThreshold, keywords, endpointing), voice selection, conversation flow, urgency handling β plus evaluation logic and audio diagnostics that require knowing the Vapi artifacts API and audio signal processing. The longer it runs, the more reference data it accumulates. That's the moat.
| Tool | What it does |
|---|---|
list_agents | Lists the assistants on the account (id, name, model, voice, transcriber) β the entry point to find an assistantId. |
deploy_agent | One tool = one full vertical deployment. deploy_agent(vertical: elagueur|plombier, company, extraKeywords) creates a complete Vapi assistant: prompt, voice, transcriber, keywords, greeting. |
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 billing β pure prompt evaluation. Global hard checks on every scenario: phone fidelity (any number the agent speaks must be one the caller gave β catches hallucinated numbers that plain "did it spell the digits?" checks miss) and anti-leak (template brackets never reach the caller's ear). One hard failure = verdict FAIL, whatever the grade. |
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 | Prompts as code. snapshot captures the live prompt into local history, diff compares two versions, rollback pushes an old prompt back to Vapi. |
regression_gate | CI for prompts. Runs run_eval and blocks the update if the score regressed vs the stored baseline. Returns allow/deny with the reason. |
Prompt snapshots (prompt_diff) are stored in ./.standard-vocal/ of the directory you launch from β override with STANDARD_VOCAL_STATE_DIR.
β creates the assistant with:
nova-3 with numerals: true, confidenceThreshold: 0.5, and keywords boosted for the business's real streets/townsThen:
β runs 4 scripted scenarios (standard quote, address correction, storm emergency, solicitation) and returns a /100 grade with per-check pass/fail.
src/deploy.ts β vertical deploymentsrc/eval.ts β self-testing enginesrc/forensics.ts β audio analysissrc/versioning.ts β prompt history / diff / rollbackverticals/templates.json β vertical templates (prompt, voice, transcriber, keywords)evals/scenarios.json β scripted eval scenarios with weighted checksregression_gate integration with CI (GitHub Action)audio_forensicsmcp-remote variant (like Vapi's mcp.vapi.ai)Built by Guillaume Jean Hussong Β· Standard Vocal β the phone agent factory.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/guillaumehussong-standard-vocal-mcp)<a href="https://allmcps.com/mcp/guillaumehussong-standard-vocal-mcp"><img src="https://allmcps.com/api/badge/guillaumehussong-standard-vocal-mcp?style=directory" alt="Standard Vocal MCP on AllMCPs" /></a>