voicemeeter-mcp
An MCP server for controlling Voicemeeter (Basic, Banana, or Potato) on Windows: strip and bus gains, mutes, output routing, live levels, macro buttons, presets, and audio-engine restarts.
README
voicemeeter-mcp
An MCP (Model Context Protocol) server for controlling Voicemeeter (Basic, Banana, or Potato) on Windows: strip and bus gains, mutes, output routing, live levels, macro buttons, presets, and audio-engine restarts.
- Uses the official Voicemeeter Remote API (via voicemeeter-api).
- Windows-only, local-only — the Remote API is an in-process DLL, so this server must run on the PC where Voicemeeter runs. From another machine, connect over SSH stdio (example below).
- Every mutating tool accepts
dry_run=trueand returns a preview instead of acting.
Quick start (on the Voicemeeter PC)
# select your edition: basic | banana | potato (default: banana)
set VM_MCP_KIND=banana
claude mcp add voicemeeter -s user -- uvx voicemeeter-mcp
From a different machine (SSH stdio):
claude mcp add voicemeeter -s user -- ssh streampc "uvx voicemeeter-mcp"
Tools
| Tool | Purpose |
|---|---|
mixer_state |
full snapshot: every strip/bus with label, gain, mute, routing |
set_strip_gain / mute_strip |
input fader control |
set_strip_routing |
send a strip to A1/A2/A3/B1/B2 outputs |
set_bus_gain / mute_bus |
output control |
get_levels |
live post-fader levels — find silent or clipping paths |
trigger_macro_button |
press a Voicemeeter macro button |
load_preset |
load a settings XML |
restart_audio_engine |
the classic crackle fix |
health_check |
connection + version |
A typical agent ask: "the game audio is too loud on stream" →
mixer_state to find the strip by label → set_strip_gain(strip, -12).
Development
pip install -e '.[dev]'
ruff check src tests && pytest
Tests run anywhere (fake Remote API); only live use requires Windows.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.