audio-mcpSAFE
Give 3D AI agents a voice and a face from any MCP client — text-to-speech, speech-to-text, audio-to-face lipsync (ARKit blendshapes), and the motion-capture clip library. Read-only over the live three.ws API; free NVIDIA lanes, no key required.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/audio-mcp
Give a 3D AI agent a voice and a face — text-to-speech, speech-to-text, audio-to-face lipsync, and the motion-capture clip library, from any MCP client.
A Model Context Protocol server that exposes the three.ws voice and animation pipeline over stdio. Make an avatar speak, let users talk back, turn that speech into a per-frame lipsync track, and browse the recorded motion-capture library — everything you need to drive a 3D agent's mouth and movement.
The speech, recognition, and lipsync lanes run on free NVIDIA NIM models (Magpie TTS, Riva ASR, Audio2Face-3D), with OpenAI as the paid TTS backstop — the same provider policy as the three.ws platform. No key required to start; point THREE_WS_BASE at a deployment and go.
Install
npm install @three-ws/audio-mcp
Or run with npx (no install):
npx @three-ws/audio-mcp
Quick start
Claude Code, one line:
claude mcp add audio -- npx -y @three-ws/audio-mcp
Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):
{f7a29b33bd98OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add audio-mcp --env THREE_WS_API_KEY=${THREE_WS_API_KEY} -- npx -y @three-ws/[email protected]Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.nojekyll
@modelcontextprotocol/sdk, zod
Gates applied: no_behavioural_pass.
f7a29b33bd98full audit observations/trust-audit/mcp-server/nirholas__audio-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | f7a29b33bd98 | SAFE | B | 89 | first audit |
Questions
What is the audio-mcp MCP server?
Give 3D AI agents a voice and a face from any MCP client — text-to-speech, speech-to-text, audio-to-face lipsync (ARKit blendshapes), and the motion-capture clip library. Read-only over the live three.ws API; free NVIDIA lanes, no key required.
Is audio-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does audio-mcp need?
It reads THREE_WS_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does audio-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/audio-mcp at 0.1.3.
How current is this page?
The grade is for one exact copy of the source (f7a29b33bd98), read on 2026-10-10. The repository is watched and re-audited when it changes.