io.github.cyanheads/musicbrainz-mcp-server

Paginate entities linked to one parent MBID. Accepted parents by target: artist → area, recording, release, release-group, work; label → area, release; release-group → artist, release; release → area, artist, label, recording, release-group, track_artist; recording → artist, release, work; work → artist. track_artist enumerates releases crediting an artist on tracks but not at release level. Artist release-groups and release-group editions embed one upstream page in get_* lookups; use this tool for the complete entity set. Recording browse returns identities, not performance attributes/dates or ordered release tracks: use musicbrainz_get_recording for work relationships and musicbrainz_get_release for tracks. Provide exactly one valid parent link. offset pages to any depth; totalCount is the exact filtered upstream entity total. Optional type/status filters apply only on supported parent pairs; preserve applied filters on continuation. Release rows carry status, other entity subtypes use type; release-groups include secondaryTypes and recordings include firstReleaseDate when available.

Artist profile by MBID: type, country, life span, gender, area with areaId, birth/formation and death/dissolution areas, IPI/ISNI identifiers, aliases, tags/genres, release-groups, band-membership / collaboration relationships, and external links. Chain areaId into musicbrainz_browse_entities link.area. Release-groups embed one upstream page (25); relationships are not capped. For the complete release-group list, call musicbrainz_browse_entities with target_type=release-group and link.artist.

Cover Art Archive images for a release or release-group MBID: front/back flags, image types, full-resolution URLs, and 250/500/1200px thumbnail URLs. limit defaults to 25 and clamps above 100; offset defaults to 0. Pages retain archive order, totalCount counts all images, and hasArt describes the full archive even on an empty page. Follow the notice for the next offset. No art is a successful empty result; an unknown MBID fails with entity_not_found after a bounded MusicBrainz check. A release-group resolves to a representative release's art. URLs are linked, never rehosted; image copyright stays with rights holders.

Label by MBID: type (Original Production, Reissue, Imprint, …), country, life span, label code (the LC number), area and areaId, IPI/ISNI identifiers, aliases, tags, ownership/imprint/distribution relationships, and external links (url-rels — Wikidata, Discogs, official site). Chain areaId into musicbrainz_browse_entities link.area. A label's releases are a potentially huge linked set (a major label can have tens of thousands), so they are NOT embedded here — enumerate them with musicbrainz_browse_entities (target_type=release, link.label).

Recording (a specific performance, distinct from the abstract work) by MBID: length, artist credits, ISRCs, one upstream page of release appearances with completeness metadata, work relationships, and performer/production credits with attributes and dates. Relationships are not capped. Enumerate releases with musicbrainz_browse_entities (target_type=release, link.recording, offset=0); embedded and browse order may differ. Browse recording by work enumerates recording entities; this tool supplies their work relationship details.

One edition by MBID: ordered media with tracks, track-specific artist credits when supplied, lengths and recording MBIDs, label + catalog number, barcode, country, release date, packaging, text representation, external links, and a cover-art availability stub. media_offset (default 0) and media_limit (default 20, no maximum) select whole media after normalization; mediaTotal and trackTotal describe the full release. Follow the notice to retrieve remaining media. The release resource retains the complete raw tracklist. Track lengths are m:ss. For image URLs, call musicbrainz_get_cover_art.

Release-group ("the album" above specific pressings) by MBID: primary type (Album/Single/EP) and secondary types (Live/Compilation), first-release date, artist credit, the list of releases (editions), tags/genres, external album links, and cover-art availability from the Cover Art Archive (image count and front/back flags for the release-group's representative release — the art musicbrainz_get_cover_art returns; use that tool for the image URLs). The embedded releases list is capped at one page (25); for the complete set of editions, call musicbrainz_browse_entities with target_type=release and link.release-group. For a specific edition's tracklist, take a release MBID from the releases list and call musicbrainz_get_release.

Work (a composition, distinct from a recording) by MBID: type, languages, ISWCs, ordered work attributes (rights-society registrations, musical key and other metadata), writers/composers/lyricists, movements, arrangements, aliases, tags, and external links. Attributes remain available when relationships are disabled. Follow work target MBIDs with this tool; direction, orderingKey, and targetDisambiguation distinguish parts and arrangements without reordering relationships. This server returns the first 25 recording relationships with their exact total and actual truncation disclosure, preserving all other relationships. Browse recording entities with musicbrainz_browse_entities (target_type=recording, link.work), then use musicbrainz_get_recording for work relationship attributes and dates; browse alone does not return those details.

Resolve a standard identifier to MusicBrainz entities without a name search — the deterministic path when you already hold an ID. id_type=isrc → recordings (a recording-level code, often shared by several recordings); id_type=iswc → works (a composition-level code); id_type=barcode → releases (UPC/EAN digits; spaces and hyphens are ignored). ISRC and ISWC hit dedicated exact endpoints; barcode is a Lucene search filter so results are ranked (exact match scores 100). The output kind field tells you which entity type came back.

Full-text search across a MusicBrainz entity type (artist, release-group, release, recording, work, label) using a Lucene query string. Returns ranked matches with MBID, name/title, disambiguation, subtype where applicable, release status, release-group secondary types, recording first-release dates, and a 0–100 relevance score (100 = exact). Release rows use status; other entity subtypes use type. Starting point when resolving a name to an MBID — chain the returned MBID into the matching musicbrainz_get_* tool. Results are in MusicBrainz score-descending order. Supports field-scoped Lucene syntax (e.g. `artist:radiohead AND country:GB`). Only the first 500 matches are accessible; narrow the query or use musicbrainz_browse_entities for complete linked sets.