deepcut

Deepcut is an AI playlist engine that turns music taste and natural-language prompts into real YouTube playlists.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Get Profile: Return the single Google/YouTube profile represented by the current authenticated connection. Use this only to identify which account is connected; it does not consume YouTube quota.
  • Auth Status: Report whether the server is authorized against a Google account, which scopes are held, and when the current access token expires. Costs 0 quota. Call this first if any write operation f
  • Quota Report: Show YouTube Data API units spent today, units remaining, and the per-endpoint cost table. Costs 0 quota. Useful before starting a large playlist build: each track costs ~150 units (100

What data it sees

Do you need an account

No: the server works without sign-in

Deepcut is an AI playlist engine that turns music taste and natural-language prompts into real YouTube playlists. It searches, resolves the best official versions, filters karaoke, covers, reactions, and sped-up edits, then creates or manages playlists on the user's authorized YouTube account.

How to connect

How to connect deepcut to Claude

The server address to paste into Claude settings:

https://deepcut--cflash18.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect deepcut to ChatGPT

The server address to paste into ChatGPT settings:

https://deepcut--cflash18.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect deepcut to Cursor

The server address to paste into Cursor settings:

https://deepcut--cflash18.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (15)

Raw names from tools/list. Only developers need these.

get_profileReturn the single Google/YouTube profile represented by the current authenticated connection. Use this only to identify which account is connected; it does not consume YouTube quota.
auth_statusReport whether the server is authorized against a Google account, which scopes are held, and when the current access token expires. Costs 0 quota. Call this first if any write operation fails with a permissions error.
quota_reportShow YouTube Data API units spent today, units remaining, and the per-endpoint cost table. Costs 0 quota. Useful before starting a large playlist build: each track costs ~150 units (100 to search, 50 to insert).
search_videosSearch for videos with optional filters. Costs 100 quota units per call plus 1 unit to hydrate metadata — this is the most expensive operation available, so prefer resolve_tracks when the goal is finding songs.
get_video_detailsFetch title, channel, duration, view count and category for up to 50 video IDs. Costs 1 quota unit per batch of 50 — effectively free, so batch generously.
list_my_playlistsList playlists owned by the authorized account, with IDs, privacy status and item counts. Costs 1 quota unit.
get_playlist_itemsList the videos in a playlist in order, with the playlistItemId needed for removal or reordering. Costs 1 quota unit per 50 items.
resolve_tracksTurn a list of song names ('Gov't Mule - Soulshine') into the best-matching YouTube video for each, scoring candidates to reject karaoke, covers, reactions, sped-up edits and hour-long loops. Returns matches with confidence scores plus an explicit list of tracks it could not resolve. Costs ~101 units per track. Use this to preview before build_playlist_from_tracks.
create_playlistCreate an empty playlist on the authorized account. Costs 50 quota units. Defaults to private; only set public when the user has explicitly asked for it.
add_videos_to_playlistAppend video IDs to an existing playlist, skipping any already present. Costs 50 quota units per video added, plus 1 per 50 existing items scanned for the duplicate check.
build_playlist_from_tracksBuild a complete playlist by resolving song names to videos, creating the playlist, and filling it in order. Returns a report of what was added and what could not be matched. Costs roughly 150 quota units per track plus 50 for the playlist — a 50-track playlist is about 7,550 of the default 10,000 daily units. Just build it for normal requests; low-confidence tracks are skipped and reported, not guessed at. Use dryRun only when the list is large enough that a bad run would exhaust the day's quota and block a retry (roughly 30+ tracks).
remove_playlist_itemsRemove items by playlistItemId (get these from get_playlist_items — the video ID will not work). Costs 50 quota units per removal. Requires confirm: true.
reorder_playlist_itemMove one item to a new zero-based position. Costs 50 quota units. Positions shift after each move, so re-read the playlist between multi-step reorders.
update_playlistChange a playlist's title, description or privacy. Costs 50 quota units. The YouTube API replaces rather than merges, so title is mandatory — pass the existing title if you only mean to change the description.
delete_playlistDelete a playlist permanently. Costs 50 quota units. Requires both confirm: true and the exact current title, as a guard against acting on a misremembered ID.