Skip to main content
Glama
Sign In
MuseScore MCP Server

MuseScore MCP Server

by ghchen99
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Get Score

get_score

Retrieve notes from the current score as LilyPond or raw JSON, paging through measures and selecting staves to inspect large scores.

Instructions

Get the notes of the current score as LilyPond (or raw JSON), a range of measures at a time. Without end_measure, returns at most 16 measures starting at start_measure; the header says how many measures the score has, so page through long scores. Use staves to read only some staves of a large score. Each bar ends with '% m.N': N is the bar's position, which is what every tool's measure parameters mean. When the score's displayed bar numbers differ (e.g. they count repeats), the displayed number follows as '(bar M)'; repeat barlines show as '|:' and ':|xN'.

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": "get_score"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNo"lilypond" for compact notation text, "json" for the raw analysislilypond
stavesNoStaff indices to read (0-based). Defaults to all staves.
end_measureNoLast measure to read (1-based, inclusive). Defaults to start_measure + 15.
start_measureNoFirst measure to read (1-based)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the 16-measure default window, that the header reports total measure count for paging, the '% m.N' bar marker convention, how displayed bar numbers appear as '(bar M)' when they count repeats, and how repeat barlines render ('|:' and ':|xN'). These are real behavioral traits an agent could not infer from the schema.

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 purpose, then defaults, then the numbering and repeat-bar notation needed to interpret the output. Every sentence is load-bearing; nothing restates the schema or the title.

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?

No output schema exists, so the description must explain what comes back, and it does — text form, bar delimiters, measure-count header, displayed-number annotations. For a four-parameter read tool with no annotations, nothing an agent needs in order to call it correctly is missing.

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 baseline is 3, but the description adds genuine meaning: the end_measure default is explained in terms of a page window, staves is motivated as a way to trim large scores, and — most importantly — it defines that measure numbers refer to the bar's physical position, which is what every tool's measure parameters mean. That cross-tool semantic is not in the schema.

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

Purpose4/5

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

The definition states a specific verb and resource — 'Get the notes of the current score' — plus the two output modes (LilyPond or raw JSON) and the paging scope. It implicitly separates itself from display-oriented siblings like show_score by framing the result as notational text, but it never names a sibling alternative explicitly.

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 concrete usage context: page through long scores when end_measure is omitted, and restrict with staves when the score is large. There is no explicit when-not or named alternative among the many sibling tools, so guidance is strong but not routing-level.

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

Deploy Server

Other Tools