AI & Machine Learning
lacuna.fm
Generates AI music and manages music generation tasks via the Lacuna API.
ENDPOINT 1
https://www.lacuna.fm/mcp
MCP server metadata
- Name
- lacuna
- Version
- 1.0.0
Lacuna generates AI music. Call `generate_music` to submit a task — it returns immediately with a `pending` task id, because rendering takes roughly 30–120 seconds. Poll `get_generation` with that id until status becomes `ready` (audio URLs are attached) or `failed`. Do not busy-loop: wait ~10 seconds between polls. Each task spends credits from the authenticated account, so confirm with the user before generating repeatedly.
Known tools 3
list_modelsList the music models available through the API, with their credit cost per task, tracks produced per task, and language coverage.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.lacuna]
url = "https://www.lacuna.fm/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"lacuna": {
"type": "http",
"url": "https://www.lacuna.fm/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: lacuna
Remote MCP URL: https://www.lacuna.fm/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"lacuna": {
"url": "https://www.lacuna.fm/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"lacuna": {
"type": "http",
"url": "https://www.lacuna.fm/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "lacuna",
"transport": "streamable-http",
"url": "https://www.lacuna.fm/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.