Skip to main content
Glama

Song registration check: MLC registration, unclaimed shares, writers, publishers and ISWCs

lookup_recording
Read-onlyIdempotent

ISRC lookup and music royalties registration check for one recording, with the song's rights data. Give exactly one of: an ISRC, a Spotify track link, a song title (optionally with the artist), or a YouTube link. Returns candidate recordings and MLC works, how each was matched and how confidently, and a verdict per recording: registered, partial (a share is unclaimed), nobody (no MLC work is linked), conflict, missing_from_bulk (an earlier copy of The MLC's bulk data showed publishers or a work link that the current copy does not; the bulk data has dropped claims that are still live, so never a finding that a share is unclaimed), or unknown. Each verdict carries dated evidence (as_of, from The MLC's bulk data snapshot) and a factual next step. Also returns what MusicBrainz records for the recording: the linked works with their ISWCs, the writers and publishers with their IPI and ISNI numbers, the earliest release's album, date, label and catalogue number, and the MusicBrainz page. With full_record true it adds every release (label, catalogue number, country and date), performer and producer credits and related recordings; that answer is many times larger. When several matches are equally likely, ambiguous is true and all are returned. Findings from registration data, not legal advice or a statement of song ownership.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "lookup_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
isrcNoISRC, 12 characters, e.g. USIR20400274 (hyphens and spaces allowed).
titleNoSong title, when no ISRC or link is available.
artistNoOptional artist name; only together with title.
full_recordNoTrue to add MusicBrainz's full record of the recording: every release with its label, catalogue number, country and date, the credits, and related recordings. Only for an ISRC or a Spotify link that resolves to one recording. Leave it out unless that detail is needed: the answer is many times larger.
spotify_urlNoSpotify track link (https://open.spotify.com/track/...) or spotify:track:... URI. Album and playlist links are not accepted.
youtube_urlNoYouTube video link; resolved from the video title, so matches are low confidence.

Output Schema

NameRequiredDescriptionDefault
notesNo
queryYes
resultsNo
ambiguousNo
candidatesNo
input_kindYes
mlc_sourceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedOutput schema / $defs / BulkGap
      Added value: +{
      +  "description": "An item on the snapshot's bulk-gap list, as the lookup reports it.",
      +  "properties": {
      +    "kind": {
      +      "$ref": "#/$defs/BulkGapKind"
      +    },
      +    "last_known_publishers": {
      +      "default": [],
      +      "items": {
      +        "$ref": "#/$defs/MLCPublisher"
      +      },
      +      "title": "Last Known Publishers",
      +      "type": "array"
      +    },
      +    "last_known_work": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Last Known Work"
      +    },
      +    "last_present": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Last Present"
      +    }
      +  },
      +  "required": [
      +    "kind"
      +  ],
      +  "title": "BulkGap",
      +  "type": "object"
      +}
    • addedOutput schema / $defs / BulkGapKind
      Added value: +{
      +  "description": "What an earlier copy of The MLC's bulk data showed that this one does not.\n\nFrom the per-snapshot list ``mlc_bulk_gaps.parquet``\n(``trackforge/mlc_bulk_gaps.py``). The MLC's bulk feed has dropped claims\nthat are still live (Brain 853ecab5), so a listed item's absence in the\nsnapshot is not evidence of absence.",
      +  "enum": [
      +    "publishers_dropped",
      +    "link_dropped"
      +  ],
      +  "title": "BulkGapKind",
      +  "type": "string"
      +}
    • addedOutput schema / $defs / MLCData / properties / bulk_gap
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/BulkGap"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedOutput schema / $defs / MLCLookup / properties / bulk_gap
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/BulkGap"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedOutput schema / $defs / MLCOtherWork / properties / bulk_gap
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/BulkGap"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • changedOutput schema / $defs / VerdictState / description
      Previous value: -"What the registration data shows for a recording, in one word.\n\nPrecedence when several apply: unknown > conflict > nobody > partial >\nregistered (``app/services/isrc/verdict.py``). Only a snapshot that was\nread can produce ``nobody``; an unreadable copy is ``unknown``."New value: +"What the registration data shows for a recording, in one word.\n\nPrecedence when several apply: unknown > missing_from_bulk > conflict >\nnobody > partial > registered (``app/services/isrc/verdict.py``). Only a\nsnapshot that was read can produce ``nobody``; an unreadable copy is\n``unknown``. ``missing_from_bulk``: an earlier copy of The MLC's bulk data\nlisted publishers on the work, or linked the recording to a work, and this\ncopy does not; the bulk data has dropped claims that are still live, so\nthe gap is not evidence that a share is unclaimed or no work is linked."
    • changedOutput schema / $defs / VerdictState / enum
      Previous value: -[
      -  "registered",
      -  "partial",
      -  "nobody",
      -  "conflict",
      -  "unknown"
      -]New value: +[
      +  "registered",
      +  "partial",
      +  "nobody",
      +  "conflict",
      +  "missing_from_bulk",
      +  "unknown"
      +]
  2. Changed2 schema fields changed
    • addedOutput schema / $defs / MLCData / properties / writers_vs_discogs
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/WriterMatch"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedOutput schema / $defs / MLCOtherWork / properties / writers_vs_discogs
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/WriterMatch"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, non-destructive and open-world, but the description goes well beyond them: it enumerates the full verdict taxonomy (registered, partial, nobody, conflict, missing_from_bulk, unknown), explains the tricky missing_from_bulk case, discloses that verdicts carry dated evidence, and warns that full_record makes the answer 'many times larger.' The only omission is any note on latency or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and inputs, then the verdict taxonomy, then the optional expansion, then a disclaimer. It is dense and the verdict sentence is a long list, but essentially every clause carries operational information; only the closing 'not legal advice' sentence is arguably boilerplate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter, open-world lookup with an output schema, the description covers inputs, matching behavior, result interpretation, the ambiguous flag, an explicit size/cost tradeoff for full_record, and the nature of the evidence. An agent could call and correctly interpret this tool without further information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: the mutual-exclusivity rule ('exactly one of') is not encoded as a oneOf in the schema, and it flags that YouTube matches are resolved from video titles and therefore low confidence. full_record's cost is also contextualized beyond the schema's own warning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'ISRC lookup and music royalties registration check for one recording, with the song's rights data.' The scope qualifier 'for one recording' plus the enumerated outputs (MLC works, verdicts, MusicBrainz data) makes it clearly distinguishable from a catalogue-wide or bulk-report tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives strong input guidance ('Give exactly one of: an ISRC, a Spotify track link, a song title..., or a YouTube link') and says when to set full_record, but never states when to use this tool rather than a sibling such as check_catalogue or request_full_report, nor any exclusions beyond the input forms.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources