Your agent's music intelligence layer. One API call turns any AI agent into a context-aware music brain — across Spotify, Apple Music, and Tidal.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · getbeatbrain.com
67tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://getbeatbrain.com/api/v1/mcp
Skill page: https://www.mcpbundles.com/skills/getbeatbrain-mcp-14b10e7b84
Explore capabilities (67)
read 6
write 2
other 17
Showing 25 of 67
Showing 25 of 67 tools from the public preview. Connect the server to inspect the full live tool list.
Get4
Plan2
Other capabilities19
Play Music
other
play_music
Start a BeatBrain music session. Interprets context and plans a set of tracks from the user's connected streaming service.
IMPORTANT: If the user has multiple streaming services connected (e.g. Spotify + Tidal), you MUST pass the "service" parameter to select which one to use. Without it, BeatBrain picks the most recently active connection, which may not be what the user wants.
For Tidal: pass service: "tidal". The response will include a deep_link (not a web_player_url) — send it directly to
Play Music — Start a BeatBrain music session. Interprets context and plans a set of tracks from the user's connected streaming service.
IMPORTANT: If the user has multiple streaming services connected (e.g. Spotify + Tidal), you MUST pass the "service" parameter to select which one to use. Without it, BeatBrain picks the most recently active connection, which may not be what the user wants.
For Tidal: pass service: "tidal". The response will include a deep_link (not a web_player_url) — send it directly to
Start Playback — Start playback for an already planned session. Use after play_music when you need explicit two-step orchestration.
Example: start_playback({ end_user_id: "user123", session_id: "sess_abc" })
Returns: { status: "playing|needs_device|playlist_ready", ... }
Search Tracks — Search for tracks using BeatBrain's intelligence. Searches the user's connected streaming service, enriches results with cultural metadata, and scores them with a 16-dimension fitness algorithm.
Example: search_tracks({ prompt: "upbeat indie for a road trip", end_user_id: "user123", limit: 10 })
Returns: { tracks: [{ spotify_uri, title, artist, fit_score, genre, energy }] }
Plan Set — Plan a complete music set with energy arcs, harmonic sequencing, and genre flow. Uses beam search to find the optimal track sequence from the BeatBrain catalog + the user's streaming service. Returns track URIs ready for playback.
Example: plan_set({ prompt: "sunset beach vibes that builds to a peak", end_user_id: "user123", track_count: 15, skills: ["harmonic-flow"] })
Returns: { set: { tracks: [...], energy_arc: [...], total_duration_ms }, scene: {...} }
Compile Objective — Compile natural-language context into a structured objective envelope (targets, constraints, weights) that downstream tools can use.
Example: compile_objective({ prompt: "late-night focus with low vocals", end_user_id: "user123" })
Returns: { objective: { targets, constraints, weights, mode }, scene }
Query Candidates — Query candidate tracks from BeatBrain search, optionally guided by a compiled objective envelope.
Example: query_candidates({ end_user_id: "user123", prompt: "afro house sunset", objective: {...}, limit: 60 })
Returns: { candidates: [...], scene }
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
What is the BeatBrain - Music Intelligence for AI Agents MCP server?
Your agent's music intelligence layer. One API call turns any AI agent into a context-aware music brain — across Spotify, Apple Music, and Tidal.
How do I connect BeatBrain - Music Intelligence for AI Agents to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate this server?
Request removal if you do not want BeatBrain - Music Intelligence for AI Agents listed here, or claim the listing if you want to manage it on MCPBundles.
Operate BeatBrain - Music Intelligence for AI Agents?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Score Candidates — Score external or queried candidates against a structured objective.
Example: score_candidates({ objective: {...}, candidates: [...] })
Returns: { scored_candidates: [...], accepted_count, rejected_count }
Sequence Tracks — Plan an ordered sequence from scored candidates using target energy progression.
Example: sequence_tracks({ objective: {...}, candidates: [...], track_count: 12 })
Returns: { sequence: [...], summary }
Simulate Plan — Run an end-to-end dry run of candidate query, scoring, and sequencing to inspect planning diagnostics before playback.
Example: simulate_plan({ end_user_id: "user123", prompt: "indie coding at night", objective: {...} })
Returns: { diagnostics, simulated_plan }
Control Playback — Control playback on the user's streaming service. Supports: pause, resume, skip, previous, seek, volume, shuffle, repeat, transfer.
Note: Only available for services with remote playback (Spotify). For Apple Music, use playlist management instead.
Use "transfer" with a device_id to move playback to a different device (e.g., from Echo Show to iPhone).
Example: control_playback({ end_user_id: "user123", action: "skip" })
Example: control_playback({ end_user_id: "user123", action: "volume", value
Report Feedback — Report user feedback on music. Feeds BeatBrain's learning engine to improve future recommendations.
Simple format: report_feedback({ end_user_id: "user123", signal_type: "like" })
Full format: report_feedback({ end_user_id: "user123", signals: [{ type: "like", track_id: "spotify_id" }] })
session_id is optional — BeatBrain will find the most recent session automatically.
Interpret Context — Convert natural language, sensor data, calendar info, and environmental signals into structured musical parameters. Shows what BeatBrain would interpret from a given context.
Example: interpret_context({ prompt: "focus mode", sensors: { heart_rate: 62, location_type: "office" } })
Returns: { scene: { genres: ["ambient", "lo_fi"], energy: 0.3, instrumental_only: true } }
Register Agent — Register your AI agent with BeatBrain. If you already have an API key, this creates a sub-agent identity under your key. If you don't have a key yet, provide an email and this will generate a new API key for you (sandbox tier, 50 req/hr).
Without API key (self-provisioning):
register_agent({ name: "Claude Music", email: "dev@example.com" })
Returns: { agent_id, api_key, tier: "sandbox" }
With existing API key:
register_agent({ name: "Claude Music", description: "Anthropic's music assista
Get Agent — Get your agent's profile, including the contextual taste genome summary showing learned preferences across different activities and times.
Example: get_agent({})
Returns: { agent_id, name, taste_genome: { global: {...}, contexts: { working: {...}, driving: {...} } } }
Get Recommendations — Get personalized track recommendations based on seed tracks, artists, or context. Uses Spotify's recommendation engine enhanced with BeatBrain's scoring.
Example: get_recommendations({ seed_tracks: ["4uLU6hMCjMI75M1A2tKUQC"], end_user_id: "user123" })
Returns: { tracks: [{ spotify_uri, title, artist, fit_score }] }
Now Playing — Get current playback state from the user's streaming service. Shows what's playing, progress, device, and session info.
For Spotify: real-time playback state. For Apple Music: last played track from history (not real-time).
When session_id is provided, BeatBrain automatically monitors remaining tracks and plans + queues continuation tracks when ≤3 remain — the music never stops. The response includes tracks_remaining and continuation_status.
Example: now_playing({ end_user_id: "user123", sessi
Connect Streaming Service — Initiate streaming service connection for a user. Returns an authorization URL that the user must visit once to grant access.
Supported services:
- spotify: Full remote playback control (play, pause, skip, volume, device transfer) + BeatBrain Web Player
- apple_music: Playlist management + BeatBrain Web Player (live DJ experience with real-time vibe switching)
- tidal: Playlist management + deep links to Tidal app/web player. No embedded BeatBrain web player (Tidal SDK limitation). Agent sends
Update Context — Smooth vibe transition — changes the mood, genre, or energy without interrupting the current song. BeatBrain auto-discovers the active session, plans new tracks for the updated context, and replaces all upcoming tracks in the session playlist while the current track keeps playing.
Example: update_context({ end_user_id: "user123", prompt: "switch to something more upbeat", energy: 0.8 })
session_id is optional — BeatBrain auto-discovers the active session. Only falls back to creating a new sessi
Get Operation Status — Get status for an asynchronous MCP operation (for example update_context with wait_for_apply: false).
Example: get_operation_status({ end_user_id: "user123", operation_id: "op_abc123" })
Returns: { operation_id, status: "in_progress|completed|failed", result?, error? }
Get Taste Genome — Retrieve the contextual taste profile for a user. Shows learned preferences across different activities, times of day, and locations.
Example: get_taste_genome({ end_user_id: "user123" })
Returns: { global: { genre_affinities: {...} }, contexts: { working: {...}, driving: {...} } }
Resolve Tracks — Resolve BeatBrain catalog tracks to playable URIs on the user's connected streaming service (Spotify, Apple Music, Tidal). Uses ISRC, service IDs, and fuzzy search.
Example: resolve_tracks({ tracks: [{ id: "abc", title: "Song", artist: "Artist" }], end_user_id: "user123" })
Returns: { results: [{ id, resolved, uri, confidence, method }], service, resolved_count }
Enrich Track — On-demand enrichment for any track. Uses the full knowledge fusion pipeline (GPT-4o, MusicBrainz, Last.fm, Discogs, Wikidata) to deeply understand a track.
Example: enrich_track({ title: "Bohemian Rhapsody", artist: "Queen" })
Returns: { enrichment: { genre_tags, era, mood_tags, ... }, sources_used, external_ids }
List Skills — List available intelligence skills that modify how BeatBrain interprets context and selects tracks.
Example: list_skills({ category: "focus" })
Returns: { skills: [{ id, name, description, category }] }
Install Skill — Install a skill on an agent to modify its music intelligence behavior.
Example: install_skill({ skill_id: "deep-focus", agent_id: "agent123" })
Returns: { installed: true }
Plan Transition — Plan an optimal transition between two specific tracks. Returns timing, EQ hints, FX suggestions, and harmonic analysis.
Example: plan_transition({ from_track_id: "abc", to_track_id: "xyz" })
Returns: { transition: { start_ms, duration_ms, curve, score, eq_hint, fx }, harmonic: { score, type } }
Showing the first 25 tools — full list and schemas: Directory API.
How many tools does BeatBrain - Music Intelligence for AI Agents provide?
MCPBundles probed 67 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does BeatBrain - Music Intelligence for AI Agents require?
BeatBrain - Music Intelligence for AI Agents may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.