Sign in Book a demo
Back to Tools
Entertainment OAuth
Build Your Agent View Spotify Documentation
spotify logo

Spotify MCP Tools for AI Agents

Let an agent search music, play tracks or artists, pause or resume playback, and skip through each user's queue.

Available Tools

13 tools available in this integration

Spotify.AdjustPlaybackPosition

Adjust the playback position within the currently playing track.

Spotify.GetAvailableDevices

Get the available devices

Spotify.GetCurrentlyPlaying

Get information about the user's currently playing track

Spotify.GetPlaybackState

Get information about the user's current playback state,

Spotify.GetTrackFromId

Get information about a track

Spotify.PausePlayback

Pause the currently playing track, if any

Spotify.PlayArtistByName

Play a song by an artist and queue four more songs by the same artist

Spotify.PlayTrackByName

Play a song by name

Spotify.ResumePlayback

Resume the currently playing track, if any

Spotify.Search

Search Spotify catalog information

Spotify.SkipToNextTrack

Skip to the next track in the user's queue, if any

Spotify.SkipToPreviousTrack

Skip to the previous track in the user's queue, if any

Spotify.StartTracksPlaybackById

Start playback of a list of tracks (songs)

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "play something by Khruangbin for the next hour." Arcade helps it use the right Spotify tools without guessing track IDs, artist IDs, or playback device details.

Up to 100x fewer tokens

Spotify searches and playback reads return focused track, artist, device, and state details instead of entire catalog records. The agent gets enough context to choose music without loading large result sets into the model.

Complete the workflow end to end

Search the catalog, inspect the match, start a track list, check the active device, and control playback through one toolkit designed around the complete listening task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Spotify

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Spotify, you can implement some of these policies:

Access when tools are listed for a user
  • Hide Spotify.StartTracksPlaybackById from read-only agents, so an agent cannot start playback for users who are only allowed to inspect their account.
  • Restrict Spotify.PlayArtistByName to agents operating under the roles your IDP marks as playback managers, so unapproved automation cannot take over a user's queue.
  • Deny Spotify.PlayTrackByName to guest agents, so they cannot interrupt a user's current listening session.
Pre-execution before each tool call
  • Require human approval before Spotify.AdjustPlaybackPosition runs, so an agent cannot unexpectedly jump through a user's current track.
  • Block Spotify.PausePlayback unless the request comes from an approved playback-control workflow, so background automation cannot stop a user's music without review.
  • Require human approval before Spotify.SkipToNextTrack runs, so an agent cannot discard the track a user is currently listening to.
Post-execution after the tool returns
  • Redact device names and device identifiers from Spotify.GetAvailableDevices results, so the model cannot infer a user's personal hardware or location clues.
  • Deny the output of Spotify.GetCurrentlyPlaying, so the model cannot inspect a user's current listening activity.
  • Strip device names, device identifiers, and active-track details from Spotify.GetPlaybackState results before they reach the model.

How to use Spotify with your agent

Follow the walkthrough to connect Spotify to an MCP client and let each user authorize their own account. Then try the example prompts to control playback and search the music catalog.

Your questions, answered

A Spotify MCP server exposes Spotify capabilities as structured tools that an AI agent can call through the Model Context Protocol. After a user authorizes their Spotify account, the agent can search the catalog, inspect playback, and control playback within the granted permissions.

Spotify does not provide the MCP server used here. Arcade hosts the integration and adds per-user OAuth, a consistent way to reach Spotify from supported clients, approval workflows, response redaction, and scope controls.

Arcade agents can search Spotify's catalog, look up tracks, play tracks or an artist's music, start a list of tracks, inspect the currently playing track and playback state, list available devices, pause or resume playback, adjust the position, and skip forward or back.

Catalog searches and track lookups can use Spotify's public catalog access. Reading playback requires scopes such as user-read-currently-playing and user-read-playback-state; changing playback requires user-modify-playback-state. Request only the scopes your workflow needs.

Yes. Each user authorizes their own Spotify account through OAuth. Playback actions run under that user's authorization, so the agent can access and control only the account and permissions that user approved.

Yes. Contextual Access policies can require human approval before consequential Spotify actions such as starting playback, pausing, skipping, seeking, or resuming playback. The call proceeds only after the policy's conditions have been satisfied.

Arcade proxies Spotify API calls and does not persist your content as part of normal tool execution. OAuth credentials are brokered and stored encrypted at rest, and the model never receives them.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes Spotify access while the user's authorization remains valid. If the authorization is revoked, rotated, or can no longer be refreshed, actions stop until the user reconnects their Spotify account.

Spotify's Web API rate limits and any account or playback restrictions still apply to calls made through Arcade. The available device and active playback state can also limit whether a playback action succeeds.

Ready to actually ship your agent?

Connect your agent to Spotify with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Spotify Quickstart