The MCP server
The archive handed to agents as Model Context Protocol tools.
Fluncle serves a small, stateless Model Context Protocol server: the same archive the public API exposes, handed to agents as tools. Streamable HTTP, no sessions, no auth.
https://www.fluncle.com/mcpConnect
Point any MCP client at the endpoint. For a client that reads a config block:
{
"mcpServers": {
"fluncle": { "type": "http", "url": "https://www.fluncle.com/mcp" }
}
}Tools
The archive, as five tools:
| Tool | Does |
|---|---|
list_tracks | The latest findings, newest first. |
get_random_track | One finding, pulled at random. |
search_tracks | Search Spotify for a candidate. |
submit_track | Recommend a track for review (not a publish). |
subscribe_newsletter | Board the mothership. |
(get_recent_tracks still works as a deprecated alias of list_tracks for a window.)
submit_track is a recommendation, like the CLI's submit: it queues a track, and Fluncle listens before anything joins the archive.
How it's built
The MCP server is a thin layer over the same internal functions the /api routes use, so validation, the submission rate limit, and the submitter hash all stay identical to every other surface. An agent and a human reach the same archive, the same way.
For discovery, the MCP Server Card lives at /.well-known/mcp/server-card.json.