Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gabrielekarra/mcp-anything --skill servergit clone --depth 1 https://github.com/gabrielekarra/mcp-anythingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gabrielekarra/mcp-anything/server)<a href="https://agentmods.dev/skills/gabrielekarra/mcp-anything/server"><img src="https://agentmods.dev/badge/skills/gabrielekarra/mcp-anything/server.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00472 |
| Opus 5 | $0.00000 | $0.00236 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spotify-playlist-generator — SKILL.md
Overview
Use this MCP server to generate Spotify playlists from a user-requested duration and mood/vibe. The primary response returns selected tracks with cover art URL, song name, duration, singers/artists, album, Spotify URI, and Spotify URL.
Tools
generate_spotify_playlist
Generates a Spotify playlist candidate list from duration_minutes and mood_vibe. Set create_playlist=true to create the playlist in the current user's Spotify account.
Parameters:
duration_minutes(number, required): target playlist duration, 5 to 480 minutes.mood_vibe(string, required): natural language vibe such asrainy indie,workout,chill focus, orlate-night drive.market(string, optional): two-letter Spotify market code; defaults toUS.playlist_name(string, optional): playlist name when creating it in Spotify.create_playlist(boolean, optional): create the playlist in Spotify.public(boolean, optional): make the created playlist public.
setup_spotify_oauth
Returns a Spotify authorization URL for playlist write scopes. Use this when the server does not yet have SPOTIFY_ACCESS_TOKEN or SPOTIFY_REFRESH_TOKEN.
exchange_spotify_code
Exchanges a Spotify OAuth callback code for access and refresh tokens. Store the returned refresh token in SPOTIFY_REFRESH_TOKEN.
Usage Patterns
- Preview only: call
generate_spotify_playlistwithduration_minutes,mood_vibe, and optionalmarket. - Create in Spotify: complete OAuth setup first, then call
generate_spotify_playlistwithcreate_playlist=true. - OAuth setup: call
setup_spotify_oauth, open the returned URL, then callexchange_spotify_codewith the callback code.
Gotchas
- Creating playlists requires a user OAuth token with
playlist-modify-privateorplaylist-modify-public. - Preview generation can use Spotify client credentials, but playlist creation cannot.
- Spotify market availability can change results; use the user's country if they ask for region-specific music.
- The server does not store secrets. Configure credentials with environment variables.
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- conformance_report.json 2.2 KB
- descriptions.yaml 405 B
- Dockerfile 597 B
- domain_model.json 2.4 KB
- eval_cases.json 1.7 KB
- quick_queries.json 848 B
- skybridge/.skybridge/views.d.ts 192 B runs code
- skybridge/Dockerfile 638 B
- skybridge/index.html 373 B
- skybridge/package.json 881 B
- skybridge/pnpm-lock.yaml 86 KB
- skybridge/README.md 2.1 KB
- skybridge/src/discovery.ts 838 B runs code
- skybridge/src/server.ts 14 KB runs code
- skybridge/src/telemetry.ts 839 B runs code
- skybridge/src/views/exchange_spotify_code.tsx 2.9 KB
- skybridge/src/views/generate_spotify_playlist.tsx 11 KB
- skybridge/src/views/setup_spotify_oauth.tsx 2.4 KB
- skybridge/tsconfig.json 401 B
- skybridge/vite.config.ts 142 B runs code
- tool_spec.yaml 2.9 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 42 lines · 0 tokens per session scan A af2230d9853d
server is a skill published in the GitHub repository gabrielekarra/mcp-anything (43 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 472 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
c-music
Control Spotify playback using the spogo CLI. Play, pause, skip, search tracks/albums/playlists, manage the queue, and browse your library.
c-video
Download videos, extract audio, convert formats, and clip segments using yt-dlp and ffmpeg. Supports YouTube, Vimeo, and hundreds of other sites.
spotify-player
Terminal Spotify playback, search, queue, and device control via spogo or spotifyplayer CLI.
songsee
Identify songs by audio fingerprinting via AudD or Shazam API, with fallback to the songrec CLI.
camsnap
Capture photos from the connected camera and optionally analyze them with vision AI. Uses imagesnap (macOS) or ffmpeg (Linux).
openai-whisper
Transcribe audio files locally using the OpenAI Whisper CLI. No API key required - runs fully offline.