search_soundsLABSCO SUMMARY
Sound search that answers the licensing question in the same result.
Finding a clip is the easy half; knowing whether you can ship it is the slow half. Licence and attribution detail come back attached to each hit, so the choice and the clearance happen in one step.
What it is
An MCP server over Freesound.org that finds sound effects, ambience and music loops for a video or content workflow from a natural-language description.
What you get
- Natural-language search across the Freesound library (search_sounds)
- Duration, tags and description on each result, so a clip can be judged before it is downloaded
- Licensing information on every result, which is what decides whether attribution is required
- Preview URLs for immediate playback
Requirements
A Freesound account and an API key, applied for at https://freesound.org/api/apply/ and passed as FREESOUND_API_KEY. Runs from Docker, or locally with Python 3.10+ and uv.
Setup effort
Run a container — build the image from the repository, then point your client at it
USE CASES
01
Finding a sound effect for a specific moment in an edit
Describe the sound you want and read back candidates with their durations.
02
Picking background ambience for a scene
Search for the setting and filter by length against the shot.
03
Making sure a clip can be used before you build on it
The licence and attribution terms arrive with the search result.
04
Auditioning several options quickly
Each result carries a preview URL, so candidates can be heard before anything is downloaded.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. search_sounds returns metadata, preview URLs and licensing; max_results ranges from 1 to 30, default 10. Only the stdio transport ships.
Requires
- docker on PATH
- Python 3.10+
- FREESOUND_API_KEY in your environment
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
Build the image from the repository, then point your client at it.
Server setup
TERMINAL
git clone https://github.com/johnkimdw/freesound-mcp-server.git
cd freesound-mcp-server
docker build -t freesound-mcp .Add the mcpServers entry with your FREESOUND_API_KEY to claude_desktop_config.json
MCP Clients
Claude Desktop — Docker
CLAUDE DESKTOP — DOCKER · JSON
{
"mcpServers": {
"freesound": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"FREESOUND_API_KEY",
"freesound-mcp"
],
"env": {
"FREESOUND_API_KEY": "<YOUR_FREESOUND_API_KEY>"
}
}
}
}Claude Desktop — uv
CLAUDE DESKTOP — UV · JSON
{
"mcpServers": {
"freesound": {
"command": "<YOUR_PATH_TO_UV>",
"args": [
"--directory",
"<YOUR_PATH_TO_FREESOUND_MCP_SERVER>",
"run",
"freesound-mcp"
],
"env": {
"FREESOUND_API_KEY": "<YOUR_FREESOUND_API_KEY>"
}
}
}
}
