Server data from the Official MCP Registry
Voice interface for Claude Code: talk to your agent and it talks back while it works.
About
Voice interface for Claude Code: talk to your agent and it talks back while it works.
Security Report
The MCP server is well-structured with appropriate authentication (xAI API key required) and permissions matching its voice-coding use case. However, there are several code quality concerns including subprocess invocation with user-controlled scripts, potential path traversal risks despite guards, and sensitive data exposure in HTTP responses that warrant attention. Supply chain analysis found 9 known vulnerabilities in dependencies (2 critical, 4 high severity).
5 files analyzed · 17 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
Environment variable: XAI_API_KEY
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-noisy-noisy-coding": {
"env": {
"XAI_API_KEY": "your-xai-api-key-here"
},
"args": [
"-y",
"noisy-coding-hud"
],
"command": "npx"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
noisy-coding
Talk to Claude Code while it works — Jarvis-style voice coding. It's your voice that's noisy, not your code.
Claude speaks short summaries aloud. An always-on listener turns your speech into messages Claude receives mid-task, without stopping it — no push-to-send, no copy-pasting transcripts. Step away from the keyboard and keep steering your agent.
Why you'll like it
- Interrupt-free flow — speak while Claude is working; your words land in the running session, not a text box.
- Hands-free reviews — Claude reads its findings aloud; you answer from across the room.
- Live "tactical HUD" dashboard — conversation log with replay/recall, real-time oscilloscope, mute buttons, costs and latencies at a glance.
- Per-agent character — voice, speed, and personality dials for every agent, all from the dashboard.
- Nothing to configure in files — API key, devices, language, push-to-talk: everything lives in the UI and persists.
- Never talks over you — one voice at a time; speech you missed parks as UNHEARD and a CATCH UP button replays it.
Speech-to-text and text-to-speech run on the Grok (xAI) Voice API — extremely cheap in practice (a small one-time budget lasts months of daily use).
Install in 2 minutes
The backend ships as a hardware-free Docker image
(noisy/noisy-coding):
the dashboard browser tab is the microphone and the speaker. You need
Docker and a browser — no Python, no git, no environment variables.
# terminal: marketplace + plugin in one line
claude plugin marketplace add noisy/noisy-coding && claude plugin install noisy-coding@noisy
# inside Claude Code (new session):
/noisy-coding:setup
The setup command starts the published image and walks you through first contact. Then finish in the browser at http://127.0.0.1:8765: paste your xAI API key (console.x.ai) and click the amber ENABLE TAB AUDIO banner — that one click makes the tab your microphone and speaker. Keep the tab open and just talk.
Prefer staying inside Claude Code? Same thing, four commands:
/plugin marketplace add noisy/noisy-coding →
/plugin install noisy-coding@noisy → /reload-plugins →
/noisy-coding:setup.
Other setups — plain Docker without the plugin, native install with hardware mic/speakers, remote hosts, all configuration knobs — live in docs/INSTALL.md.
How it works
All speech logic lives in one listener daemon — the single owner of
the microphone, the playback queue and the speakers. The MCP server is a
thin messenger that forwards speak requests; Claude Code hooks deliver
your transcribed speech back into the session (see
docs/hooks.md).
mic (hardware or browser tab via WS :8766)
-> VAD -> Grok STT -> transcript queue -> HTTP :8765
^ polled by Claude Code hooks
speak (MCP, stdio or HTTP :8767) -> POST /speak -> daemon queue
-> Grok TTS -> speakers (hardware or browser tab)
Tools
| Tool | What it does |
|---|---|
speak(text, interrupt?) | Queues text for speech and waits until it has played. Voice/speed/language come from the daemon (dashboard character), not the call. |
announce(text) | Fire-and-forget variant: returns immediately, plays in the background. |
change_voice(voice_id) | Deliberately switches this agent's voice (persists, shows on the dashboard). |
list_voices() | Lists the built-in Grok voices (ara, eve, leo, rex, …). |
Docs
- docs/INSTALL.md — plain Docker, native install, remote hosts, environment variables, development commands
- docs/hooks.md — how Claude hears you
- docs/ports.md — what each port is for
- docs/local-development.md — hacking on noisy-coding itself
License
MIT © Krzysztof Szumny
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Fetch
Freeby Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
FinAgent
Freeby mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.