Getting Started
Get SK Wwise MCP installed and connected to your Wwise project.
Prerequisites
- Python 3.12+
- Wwise 2024.1+ with WAAPI enabled
- uv (recommended) or pip
- An MCP-compatible AI agent (Claude Code, Cursor, VS Code Copilot, etc.)
Optional:
- ffmpeg — for auto-converting non-WAV audio formats during import
Installation
Windows
git clone https://github.com/silver-rain-dev/sk-wwise-mcp
cd sk-wwise-mcp/sk-wwise-mcp
setup.batmacOS / Linux
git clone https://github.com/silver-rain-dev/sk-wwise-mcp
cd sk-wwise-mcp/sk-wwise-mcp
./setup.shThe setup script will:
- Install dependencies via
uv(orpipas fallback) - Let you choose which servers to enable
- Generate a
.mcp.jsonwith the correct paths
Manual Installation
If you prefer manual setup:
cd sk-wwise-mcp/sk-wwise-mcp
uv sync
# or: python -m venv .venv && .venv/Scripts/pip install -e .Then add servers to your MCP configuration (.mcp.json for project-level, or ~/.claude.json for global):
{
"mcpServers": {
"sk-wwise-browse": {
"command": "/path/to/.venv/Scripts/python.exe",
"args": ["/path/to/mcp_browse/server.py"]
}
}
}Enable WAAPI in Wwise
Most servers require WAAPI to be running:
- Open Wwise
- Go to Project > User Preferences
- Check Enable Wwise Authoring API
- Restart Wwise if prompted
Verify the Connection
Once configured, ask your AI agent:
Ping Wwise to check if it’s available.
If the connection is working, you’ll get a confirmation with the Wwise version and project name.
Next Steps
- Explore servers and tools to see what’s available
- Set up role-based access for your team
- Try common workflows to get productive quickly