Skip to main content
Glama

Recognize sheet music

recognize_sheet_music

Recognize a PDF or image of sheet music and return its MusicXML with a summary (pages, parts, measures, warnings). Give exactly one of url, attachment, file_base64 or path. A file on the user's own machine (a remote server cannot read it, and a PDF is too big for base64): use get_upload_link instead. Calls the ScanSing API, see https://scansing.app/mcp/.

Input Schema

NameRequiredDescriptionDefault
urlNohttp(s) URL of a PDF or image of sheet music
modeNomerged (default): one MusicXML; collection: a songbook, one MusicXML per number (see files)
pathNolocal file path; only when this server runs on the same machine (stdio)
pagesNoPDF pages to recognize, e.g. '3' or '3-5'
labelsNowrite each note's name under it as a lyric line: letters (C♯, B♭), solfege-fixed (Do…Si, Do is always C), movable-do (Do is the tonic), degrees (1…7 of the scale, ♭3) or kalimba (the tines' numbers); default none
save_toNolocal path to write the MusicXML to (stdio only); default: next to `path`
filenameNoname for the score, e.g. 'hosanna.pdf'
attachmentNoa PDF or image the user attached to the chat (ChatGPT fills this in: download_url, file_name)
labels_keyNowith labels movable-do, degrees or kalimba: the key they count from, e.g. 'E minor'; default: read off the music
file_base64Nothe file itself, base64 (a data: URL is fine)
include_musicxmlNoreturn the MusicXML text inline; default: when it is small and not saved to a file

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / labels / description
      Previous value: -"write each note's name under it as a lyric line: letters (C♯, B♭) or solfege-fixed (Do…Si, Do is always C); default none"New value: +"write each note's name under it as a lyric line: letters (C♯, B♭), solfege-fixed (Do…Si, Do is always C), movable-do (Do is the tonic), degrees (1…7 of the scale, ♭3) or kalimba (the tines' numbers); default none"
    • addedInput schema / properties / labels_key
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 20,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "with labels movable-do, degrees or kalimba: the key they count from, e.g. 'E minor'; default: read off the music",
      +  "title": "Labels Key"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / labels
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 40,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "write each note's name under it as a lyric line: letters (C♯, B♭) or solfege-fixed (Do…Si, Do is always C); default none",
      +  "title": "Labels"
      +}
  3. Changed10 schema fields changed
    • removedInput schema / $defs / Attachment / properties / file_id / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / $defs / Attachment / properties / file_id / default
      Removed value: -null
    • addedInput schema / $defs / Attachment / properties / file_id / type
      Added value: +"string"
    • removedInput schema / $defs / Attachment / properties / file_name / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • changedInput schema / $defs / Attachment / properties / file_name / default
      Previous value: -nullNew value: +""
    • addedInput schema / $defs / Attachment / properties / file_name / type
      Added value: +"string"
    • removedInput schema / $defs / Attachment / properties / mime_type / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • changedInput schema / $defs / Attachment / properties / mime_type / default
      Previous value: -nullNew value: +""
    • addedInput schema / $defs / Attachment / properties / mime_type / type
      Added value: +"string"
    • changedInput schema / $defs / Attachment / required
      Previous value: -[
      -  "download_url"
      -]New value: +[
      +  "download_url",
      +  "file_id"
      +]
  4. Changed2 schema fields changed
    • addedInput schema / $defs
      Added value: +{
      +  "Attachment": {
      +    "description": "A file the user attached in ChatGPT, as ChatGPT hands it to a tool.",
      +    "properties": {
      +      "download_url": {
      +        "title": "Download Url",
      +        "type": "string"
      +      },
      +      "file_id": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "title": "File Id"
      +      },
      +      "file_name": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "title": "File Name"
      +      },
      +      "mime_type": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "title": "Mime Type"
      +      }
      +    },
      +    "required": [
      +      "download_url"
      +    ],
      +    "title": "Attachment",
      +    "type": "object"
      +  }
      +}
    • addedInput schema / properties / attachment
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/Attachment"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "a PDF or image the user attached to the chat (ChatGPT fills this in: download_url, file_name)"
      +}
  5. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false), and the description adds genuinely useful context beyond them: the call goes to an external ScanSing API, local paths only work in stdio mode, and a PDF is too large for base64. It does not mention latency, cost/quota (get_usage exists), or whether the result is immediate or retrieved later.

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

Conciseness5/5

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

Front-loaded with the action and its output, then the input constraint, then the alternative, then the API note. Each sentence adds a distinct decision-relevant fact; the parentheticals carry real content rather than filler.

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

Completeness4/5

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

With an output schema present, the description need not explain return values, and it covers the tricky parts of an 11-parameter, zero-required tool (source selection, local-file limits). The one missing piece is the relationship to get_recognition/get_musicxml, which the agent would need to know to use the result after recognition.

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 description coverage is 100%, so the baseline is 3; the description earns an extra point by stating the mutual-exclusivity rule for url/attachment/file_base64/path, which the schema does not enforce. Other parameters (mode, labels, save_to, filename) are left entirely to the schema, so it does not fully compensate for selection subtleties.

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?

Names a specific verb and resource ('Recognize a PDF or image of sheet music') and states the concrete return ('MusicXML with a summary (pages, parts, measures, warnings)'). It also routes away from get_upload_link for local files, so an agent can distinguish it from at least one sibling without opening a schema.

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

Usage Guidelines4/5

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

Gives an explicit input constraint ('Give exactly one of url, attachment, file_base64 or path') and an explicit alternative with its trigger condition ('A file on the user's own machine ... use get_upload_link instead'). It never addresses the async sibling flow (get_recognition, get_musicxml, export_score), which is the main remaining selection ambiguity.

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