MCP: Spotify Music & Playlist Intel

A Model Context Protocol (MCP) server wrapping spotify-music-intel. Give an AI agent (Claude, GPT, LangChain, LlamaIndex, Cursor) six clean music-intel tools - charts, playlist placements, monthly listeners, momentum - reconstructed from Spotify's logged-out public surface with no Spotify API token (the data Spotify's Nov-2024 endpoint cull and 250k-MAU quota wall locked away).

Tools

Tool	Args	Returns
get_track	url_or_id	Track metadata (artists, release date, duration, preview).
get_artist	url_or_id, include_metrics	Artist + top tracks + monthly listeners / followers + momentum proxy.
get_album	url_or_id	Album metadata + full tracklist.
get_playlist	url_or_id, include_metrics	Playlist metadata + full tracklist + follower count.
get_charts	region	Public Top 50 chart for a region (ranked tracks, trajectory on schedules).
get_playlist_placement	track_url_or_id, against_playlists	Which playlists a track sits on + summed follower reach.

Modes

• list_tools - emit the tool catalog (name, description, JSON schema) + the agentic-payment descriptor. Free.
• call_tool - invoke one tool: { "mode": "call_tool", "tool": "get_charts", "args": { "region": "us" } }.
• batch - up to 10 {tool, args} calls in one run.

Connect it to an MCP client

This Actor is exposed as a remote MCP tool through Apify's hosted MCP server. Point any MCP-compatible client (Claude Desktop, Cursor, VS Code, or an OpenAI / LangChain / LlamaIndex agent) at Apify's server with this Actor enabled:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=seibs.co/mcp-spotify-music-intel",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Get a token (free) from Apify Console -> Settings -> API & Integrations. The Actor then appears as a callable tool. Run mode=list_tools first (free) to fetch every tool's live JSON schema, then call one:

{ "mode": "call_tool", "tool": "get_track", "args": { } }

Prefer a direct call? Hit the Actor straight through the Apify API / SDK - no MCP client required:

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("seibs.co/mcp-spotify-music-intel").call(run_input={
    "mode": "call_tool", "tool": "get_track", "args": {},
})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Pricing

Flat $0.005 per MCP tool call (mcp_tool_call). The upstream spotify-music-intel actor bills its own events (track_or_artist_record $0.005, playlist_placement_enrichment $0.010, momentum_signal $0.012) to the same run as pass-through.

Agentic payments (x402 / Skyfire)

This server is x402 (USDC on Base) and Skyfire ready: an AI agent can pay per tool call with no pre-provisioned token once the operator enables MCP monetization. The capability is advertised in the list_tools catalog under payments. Configure via env: X402_ENABLED, X402_PAY_TO_ADDRESS, SKYFIRE_ENABLED, SKYFIRE_SELLER_ID.

Data & legal posture

Logged-out, public-only catalog metadata. No login, no account, no Spotify token (the anonymous web-player token endpoint is forbidden by Spotify's Developer Terms; the internal API is not used). Monthly listeners / follower counts come from the rendered entity page and fail soft to null when the browser tier is unavailable. Polite rate limits; PII minimized to public artist / owner display names. Respect Spotify's ToS and your local laws.