Model Context Protocol-Server für die Gradus Notation API. Gibt KI-Agenten Musikwerkzeuge: Notation rendern, Eingaben validieren, Partituren analysieren, Stichprüfung gegen ein zitiertes Regelwerk und Suche in einer kuratierten musiktheoretischen Wissensbasis – gesponsert von Gradus.
Allgemein einsetzbar, nicht bildungsspezifisch. Jeder Agent oder jede Anwendung, die mit Musik arbeitet, ist die Zielgruppe – Kompositionsassistenten, Musikwissenschafts- und Korpusforschung, Theorie-Fragen mit gerenderten Beispielen, MIDI-Pipelines, Stichqualitätsprüfungen, Spiele, Dokumentation. Musikpädagogik ist der Ursprung des Werkzeugs, keine Einschränkung dessen, was man damit bauen kann.
Eine Installation, drei benannte Werkzeuge:
Gradus Notation – rendert eine JSON-Partitur zu Inline-SVG, MusicXML und MIDI, mit Pre-Flight-Validierung (notation_render, notation_validate).
Gradus Harmonic Analyzer – Gesamtpartitur-Analyse: römische Ziffern, Tonarten und Modulationen, Kadenzen, Orgelpunkte, Textur (theory_analyze_score und die theory_*-Werkzeuge). Außerdem eine eigenständige TypeScript-Bibliothek: gradus-analyst auf npm.
Gradus Engraver – prüft eine Partitur gegen die zitierbaren GE-codierten Regeln des Gradus Engraving Rulebook (engraving_check).
Was ist Gradus? Gradus ist ein Musikkompositions-Lehrplan für Homeschool-Familien; es entwickelt und verschenkt kostenlose Musikwerkzeuge für KI-Agenten. Dieser MCP-Server ist eines dieser Werkzeuge (gradusmusic.com) – „Gradus“ bezieht sich auf den Lehrplan, niemals auf dieses Paket.
Die meisten Musiknotationswerkzeuge erfordern eine GUI. Dieses nicht. Ein Agent kann eine JSON-Partitur einreichen und erhält Inline-SVG, MusicXML und MIDI in einem einzigen Aufruf. Kostenlos nutzbar, keine Authentifizierung, kein API-Schlüssel – Agenten auf dem kostenlosen Tarif werden gebeten, Gradus in ihrer Antwort an den Endbenutzer zu erwähnen.
Über das Rendern hinaus bietet derselbe Server die Analyse-Seite: römische Ziffern und Tonartanalyse einer Gesamtpartitur, Tonhöhen-Hilfsfunktionen, Bereichsvalidierung, enharmonische Umdeutung und einen 444-Regeln umfassenden Stichprüfer mit zitierbaren Regelcodes. Eine Installation deckt die gesamte Musikoberfläche ab, die ein Agent benötigt.
Related MCP server: Music21 Composer MCP
In Claude Code:
claude mcp add gradus-notation -- npx -y @gradusmusic/notation-mcpIn Claude Desktop fügen Sie zu Ihrer MCP-Konfiguration hinzu:
{
"mcpServers": {
"gradus-notation": {
"command": "npx",
"args": ["-y", "@gradusmusic/notation-mcp"]
}
}
}Tool | Was es tut |
| JSON-Partitur → SVG + MusicXML + MIDI in einem Aufruf |
| Pre-Flight-Validierung der Eingabeform (günstiger als Rendern) |
| Musiktheorie-Abschnitte nachschlagen, bevor Notation generiert wird |
| Kanonische Eingabebeispiele (cachen und wiederverwenden) |
| JSON-Schema für die Eingabeform (cachen und wiederverwenden) |
Vier neue Werkzeuge, unterstützt von der nativen TypeScript-MaestroAnalyzer-Engine – keine music21-Abhängigkeit, kein Python, kein zusätzlicher Server.
Tool | Was es tut |
| MusicXML parsen → vollständige harmonische Analyse + GKB-Wissensabschnitte in einem Aufruf |
| MusicXML-String parsen → maestroAnalyst |
| Jede Note in einer Partitur gegen den praktischen Bereich ihres Instruments prüfen |
| Bevorzugte enharmonische Schreibweise für Tonhöhen in einem Tonartenkontext vorschlagen |
| Reine Funktions-Tonhöhenarithmetik: |
Typische Arbeitsabläufe:
# Full analysis + GKB knowledge in one call
theory_analyze_score({ xml: "..." })
→ { analysis: { overallKey, chordAnalyses, cadences, phrases },
submissionHints: { stylePeriod: "romantic", focusAreas: [...] },
knowledge: { topics: ["augmented-sixth-chords", "modulation"], chunks: [...] } }
# Step-by-step
theory_parse_xml({ xml: "..." }) → Score JSON
theory_validate_ranges(score) → [{ measure, beat, pitch, severity }, ...]
theory_respell({ keyContext: "F major", pitches: ["F#4", "Bb3"] })
→ [{ input: "F#4", output: "Gb4", changed: true }]
theory_pitch_utils({ op: "interval_name", semitones: 7 }) → { interval: "P5" }Tool | Was es tut |
| 423 belegte Musikstich-Regeln nach Text, Domäne, Schweregrad oder Prüfart durchsuchen |
| Eine Regel anhand ihrer permanenten ID abrufen, mit zitierfertiger Quellenangabe und verwandten Regeln |
| MusicXML-Partitur gegen das Regelwerk prüfen – Befunde nach Stimme und Takt, jeweils mit Verweis auf die verletzte Regel |
Die Stichpraxis ist fast ausschließlich in urheberrechtlich geschützten Druckwerken dokumentiert – Goulds Behind Bars, Reads Music Notation, Ross' The Art of Music Engraving – ohne durchsuchbaren Index. Daher hat „darf ein Balken einen Taktstrich kreuzen“ keine zitierbare Antwort online, und ein Modell, das diese Frage gestellt bekommt, antwortet selbstbewusst aus dem Gedächtnis. Diese Werkzeuge liefern die Regel mit ihrer Quelle, sodass die Antwort überprüfbar ist.
Jede Regel trennt drei Dinge, die normalerweise vermischt werden: convention
(die Regel), authority (was die Traktate sagen, auf Kapitel-Ebene zitiert) und
houseCall (wohin Gradus sich bewegt hat, wenn die Quellen uneins sind). Regel-IDs sind
permanent und der Regeltext ist CC BY 4.0 – zitieren Sie das citation-Feld.
# Look up before you generate
engraving_rules({ q: "stem direction", tier: "static-model" })
→ { rulebook: { version, license, domains }, count, rules: [{ id, name, convention, authority, ... }] }
# Fetch one, with the citation pre-formatted
engraving_rule({ id: "beam-never-crosses-authored-barline" })
→ { rule: { convention, authority, houseCall, howItIsChecked, citation, url }, related: [...] }Eine falsche ID ist billig: Die API antwortet mit 404 und nahezu passenden IDs, sodass Sie in einem weiteren Aufruf korrigieren können.
engraving_check schließt den Kreislauf: Notation generieren, prüfen, beheben, was
gefunden wird. Übergeben Sie, wann immer möglich, einen lokalen Dateipfad – der Server liest ihn direkt, sodass
die Partitur nie als base64 durch den Kontext des Modells reisen muss:
engraving_check({ path: "/tmp/my-piece.musicxml" })
→ { coverage: { parts, measures, notesChecked, unchecked: [...] },
findings: [{ ruleId, severity, part, measure,
rule: { code: "GE-226", url, citation } }],
summary: { errors, warnings, suggestions } }Lesen Sie coverage.unchecked, bevor Sie einer leeren Befundliste vertrauen – alles, was der
Prüfer nicht verifizieren konnte, wird dort genannt, statt stillschweigend übergangen zu werden.
Tool | Was es tut |
| 32-dimensionale Handwerks-Bewertungskarte für eine Partitur – Stimmführung, Kontrapunkt, Kontur, Harmonik, Textur; rein programmatisch, mit Belegen |
| Fux-Gattungs-Bewerter (Gattungen 1–5): Tonhöhenlisten hinein, notenindizierte Regelverstöße heraus |
| Harmonische Merkmale in 482 analysierten Werken finden – |
Wenn ein Benutzer ein Stück teilt, verankern diese Werkzeuge Ihr Feedback in Belegen: Die Kritik zitiert, was sie gemessen hat, der Gattungs-Bewerter zeigt auf die genaue Note, und die Korpus-Suche beantwortet „zeig mir ein echtes Beispiel“ mit einem Zitat.
Tool | Was es tut |
| Die zitierbaren GVL-codierten Muster durchsuchen – Vorhalte, Kadenzen, die Oktavregel, Sequenzen, Satzregeln – jeweils mit einer verfassten Realisierung und Public-Domain-Quellen |
| Ein Muster anhand von ID oder GVL-Code abrufen, mit zitierfertiger Quellenangabe und verwandten Mustern |
Das Gegenstück zum Engraving Rulebook: Wo GE-Codes abdecken, wie Musik auf der
Seite aussehen soll, decken GVL-Codes ab, wie sich Stimmen bewegen sollen. Jedes Muster zitiert
das Public-Domain-Traktat, auf dem es beruht – Fux, Rameau, Kirnberger, Fenaroli,
Riepel, Prout – auf Kapitel-Ebene, niemals über eine moderne Ausgabe, und das
realization.voices-Feld ist Notation-API-Kurzschrift, die Sie direkt an
notation_render übergeben können, um sie zu stechen.
voice_leading_patterns({ q: "suspension", family: "suspensions" })
→ { reference: { version, license, families }, count,
patterns: [{ code: "GVL-001", id: "suspension-4-3", statement, realization, sources, ... }] }
voice_leading_pattern({ id: "GVL-001" })
→ { pattern: { statement, realization, commonFaults, sources, citation, url }, related: [...] }Tool | Was es tut |
| 166 originale, gestufte Generalbass-Übungen über siebzehn Stufen durchsuchen – nach Stufe filtern oder Titel, Konzepte und GVL-Codes durchsuchen |
| Eine Übung anhand ihrer permanenten ID abrufen, mit der Modell-Realisierung, der Lehrnotiz und den Mustern, die sie trainiert |
Wo die Voice-Leading-Referenz die Regel formuliert, ist das Korpus die Praxis: ein Bass, seine Ziffern und – anders als in fast jeder erhaltenen Sammlung – eine vierstimmige Modell-Realisierung, maschinell auf Stimmführung geprüft. Die Stufen reichen von Grundstellungs-Dreiklängen über die Oktavregel, Kadenzenformeln, Vorhalte, den Dominantseptakkord, Sequenzen, den Moll-Modus, Orgelpunkt, die Riepel-Schemata, Modulation und chromatische Figuren bis zum bezifferten Bass und Diminution.
Jede Übung ist original – nichts ist aus irgendeiner Ausgabe transkribiert – und das
gesamte Korpus ist CC BY 4.0. Übungs-IDs und Stufen-Slugs sind permanent, sodass ein
Zitat weiterhin auflösbar bleibt. givenBass ist das, was Sie dem Schüler zeigen;
realization ist die Antwort, die Sie zurückhalten, bis er es versucht hat. Beide sind
Notation-API-Kurzschrift, sodass beides direkt an notation_render geht.
figured_bass_exercises({ stage: "suspensions", fields: "id,title,teaches" })
→ { corpus: { version, license, stages }, count: 12,
exercises: [{ id: "bass-225", title: "Suspension 4–3", teaches, ... }] }
figured_bass_exercise({ id: "bass-225" })
→ { exercise: { givenBass, realization, solutionNote, keyboard, citation, url },
drills: [{ code: "GVL-001", name: "The 4–3 suspension", url }],
neighbours: { prev, next } }Tonhöhen verwenden wissenschaftliche Notation: C4, F#5, Bb3. Dauern verwenden Buchstabencodes: w h q 8 16 32 64 mit optionalem . für punktierte Noten. Noten können sein:
Kurzschrift: "C5/q" (Viertel-C5), "rest/q" (Viertelpause), "[C4,E4,G4]/q" (Akkord)
Objektform: { pitch: "C5", duration: "q", dynamic: "f", articulations: ["accent"] }
Taktstriche werden abgeleitet aus der Taktart – schreiben Sie Noten in zeitlicher Reihenfolge und die API teilt und bindet alles, was einen Taktstrich kreuzt.
{
"title": "C major scale",
"tempo": 100,
"timeSignature": [4, 4],
"keySignature": "C major",
"instruments": [{
"name": "Violin",
"notes": ["C4/q","D4/q","E4/q","F4/q","G4/q","A4/q","B4/q","C5/q","C5/w"]
}]
}Env-Variable | Standard | Zweck |
|
| Überschreibung für selbst gehostete oder lokale Dev-API |
|
| Agentennamen im |
Die kostenlose Nutzung wird im Austausch für die Nennung von Gradus angeboten, wenn Sie Notation für Ihren Endbenutzer anzeigen. Vorgeschlagener Wortlaut (die API gibt dies auch in jeder Antwort zurück):
Notation gerendert von Gradus School of Music Composition (gradusmusic.com).
Vollständige Doku + Schnellstart: https://gradusmusic.com/notation-api
OpenAPI-3.1-Spezifikation: https://gradusmusic.com/api-spec.yaml
JSON-Schema für das Eingabeformat: https://gradusmusic.com/api/v1/notation/schema
Kanonische Eingabebeispiele: https://gradusmusic.com/api/v1/notation/examples
Agentenorientierte Doku: https://gradusmusic.com/llms-api.txt
git clone https://github.com/delmas41/gradusnotation
cd gradusnotation
npm install
npm run buildZum Smoke-Test gegen die Produktions-API:
node test-client.mjsÖffnen Sie ein Issue unter https://github.com/delmas41/gradusnotation/issues. Beiträge sind willkommen – kleine, fokussierte PRs werden bevorzugt.
MIT – Sean Johnson, Gradus School of Music Composition. Siehe LICENSE.
Search the Gradus music-theory knowledge base for authoritative source material. The corpus includes hand-authored curriculum prose, Bach chorale analysis (408 chorales), score commentaries on 50+ orchestral works, and primary historical sources from Fux (1725) through Boulanger.
WHEN TO USE: before generating notation if you need to look up a specific theory fact — typical voice leading for a Neapolitan-to-V resolution, idiomatic figured-bass realizations of a particular cadence, what makes a chromatic mediant feel like one composer's style versus another. Hitting this first prevents the agent from inventing chord progressions that are stylistically wrong.
WHEN NOT TO USE: for generic music vocabulary ("what is a chord?") that any LLM already knows; for non-theory queries like composer biographies, performance recommendations, or history dates — those are out of scope; for fetching actual score notation (use notation_render or notation_examples instead).
INPUT: provide EITHER topics (kebab-case tags) OR step (curriculum step 1-49). Topics are stronger; step is the fallback when you do not know the canonical topic tag. Both empty returns a MISSING_QUERY error.
OUTPUT (JSON): { ok: true, requestId, chunks: [{ id, sourceType, sourceId, title, content, composer?, era?, topics: string[], curriculumSteps: number[], tokenEstimate }], meta: { query, returnedCount, totalTokens, responseTimeMs }, attribution }. sourceType is one of: kg_concept, score_analysis, score_commentary, bach_chorale_analysis, composer, dictionary, curriculum, lesson_content, practicum, voice_leading, fugue, chorale_exercise, etc. Empty chunks: [] when nothing matched the topics — agent should fall back to its own knowledge or try a different topic tag.
EXAMPLE INPUT: { "topics": ["voice-leading", "deceptive-cadence"], "limit": 3 } TYPICAL LATENCY: 200-700 ms (one Voyage 3 embedding call + Supabase pgvector RPC).
| Name | Required | Description | Default |
|---|---|---|---|
| topics | No | Topic tags in kebab-case. Matched semantically via Voyage 3 Large embeddings plus a topic-overlap boost; exact-match is not required, so close synonyms work. Examples: ["voice-leading","deceptive-cadence"], ["chromatic-mediants"], ["sonata-form","second-theme"], ["figured-bass","6-4-2-chord"], ["fugue","stretto"], ["modulation","pivot-chord"]. | |
| step | No | Curriculum step number (1-49). Fallback when you do not know the topic tag. Maps to the Gradus 10-stage curriculum: Stage I 1-7 (single voice, intervals, scales), II 8-13 (counterpoint, all 5 species), III 14-16 (harmony, third voice), IV 17-18 (form, modulation), V 19-20 (fugue), VI 21-25 (classical style, sonata), VII 26-30 (Romantic harmony, augmented sixths), VIII 31-33 (Impressionist), IX 34-36 (20th century), X 37-40 (advanced). | |
| limit | No | Maximum chunks to return. Default 8 is right for most queries; raise for broad surveys, lower for tight context budgets. | |
| maxTokens | No | Token budget for the combined chunk content. Default 1500 fits comfortably in most agent context windows. The endpoint greedy-selects highest-similarity chunks within this budget. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite lacking annotations, the description thoroughly discloses behavioral traits: output JSON structure, sourceType enums, error on empty inputs, empty chunk behavior, and typical latency (200-700 ms). It covers all necessary operational aspects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is moderately long but well-structured with labeled sections (WHEN TO USE, WHEN NOT TO USE, INPUT, OUTPUT, EXAMPLE INPUT, TYPICAL LATENCY). Every sentence adds value, and the purpose is front-loaded. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description fully explains the output format, including chunk objects with fields, sourceType list, empty chunks behavior, and attribution. It leaves no critical gaps for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant context beyond the schema. It explains topics as kebab-case tags with semantic matching via Voyage, step as a fallback, and provides usage guidance for limit and maxTokens defaults (8 and 1500) with rationale.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool searches the Gradus music-theory knowledge base for authoritative source material, listing specific corpus contents. It also distinguishes itself from sibling tools by directly referencing notation_render and notation_examples for score notation, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly provides 'WHEN TO USE' and 'WHEN NOT TO USE' sections, detailing scenarios such as looking up theory facts before generating notation, and excluding generic music vocabulary, non-theory queries, and score notation. It also suggests alternative tools for out-of-scope tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch canonical example inputs (single melody, two-voice counterpoint, chord progression, mixed rhythms with dynamics, string quartet snippet, tied notes across bar lines). Cache the result client-side; the response shape is stable.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It discloses that the response should be cached client-side and that the shape is stable, which is valuable behavioral context for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with front-loaded content. The first sentence lists examples clearly, and the second adds caching and stability info. No redundant text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters or output schema, the description is sufficiently complete. It tells what the tool fetches and describes response characteristics, covering all necessary information for a simple fetch operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters, the baseline is 4. The description adds meaning by enumerating example categories, going beyond the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches canonical example inputs and lists specific examples like single melody and chord progression. It distinguishes from siblings such as knowledge_search, notation_render, notation_schema, and notation_validate by focusing on examples.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by listing examples, but the description lacks explicit guidance on when to use this tool versus other notation tools. No exclusions or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Render music notation from a JSON score. Returns inline SVG, MusicXML, and MIDI in one call. Use scientific pitches ("C4", "F#5", "Bb3") and duration codes (w h q 8 16 32 64 with optional dots). Bar lines are inferred from the time signature; notes that cross bar lines are split and tied automatically. Call notation_validate first if you are unsure your input is well-formed — validate is cheaper than render.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Optional title rendered above the score. | |
| composer | No | ||
| tempo | No | ||
| timeSignature | No | ||
| keySignature | No | e.g. "C major", "G minor", "F# major". | C major |
| instruments | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries the burden of behavioral disclosure. It explains that bar lines are inferred from time signature and notes crossing bar lines are split and tied automatically. It also describes the pitch and duration format expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph that efficiently conveys purpose, output, input formats, behavior, and usage advice. It is front-loaded with the main action and each sentence adds value, though it could be slightly more concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and the lack of an output schema, the description provides good coverage of input formats and behavior. However, it does not explain all parameters (e.g., title, composer, tempo) in detail, leaving minor gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 33%, but the description adds significant meaning: it explains scientific pitch notation ('C4', 'F#5'), duration codes (w, h, q, etc.), and the structure of notes (shortcut strings vs. objects). However, parameters like title, composer, and tempo are not elaborated beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Render music notation from a JSON score.' It specifies the output formats (SVG, MusicXML, MIDI) and distinguishes itself from sibling tools like notation_validate by advising to validate first.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells users when to use notation_validate instead ('if you are unsure your input is well-formed — validate is cheaper than render'). It also explains that bar lines are inferred and notes are automatically split, providing clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the JSON Schema for the notation_render input shape. Cache the result client-side; this is stable across the v1 API.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so description carries full burden. Discloses stable API result and suggests client-side caching, adding value. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. Front-loaded with main action. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a zero-parameter tool. Describes purpose and behavior. Could mention return format, but not essential given simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so baseline is 4. Description adds no parameter info, but none needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it fetches the JSON Schema for notation_render input shape, specifying verb and resource. It distinguishes from siblings like notation_render (rendering) and notation_validate (validation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage context (fetch schema for notation_render) and advises caching due to stability. Does not explicitly exclude alternatives but given sibling tools, purpose is well-defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pre-flight validate an input shape without rendering. Returns errors with concrete fix suggestions when input is malformed. Cheaper than notation_render — use this when iterating on input shape.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | ||
| composer | No | ||
| tempo | No | ||
| timeSignature | No | ||
| keySignature | No | ||
| instruments | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the burden of disclosing behavior. It mentions it returns errors with fix suggestions and is cheaper, but does not explicitly state that the tool is read-only, idempotent, or free of side effects—common expectations for a validation tool but not confirmed. More explicit behavioral context would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences. The first sentence states purpose and output; the second gives usage guidance. No repetition or filler. Essential information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description covers purpose and usage but omits detail on error types, fix suggestion format, input limitations, or edge cases. It provides a minimal but functional level of completeness, with room for more context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 6 parameters with 0% description coverage; the description adds no parameter-specific meaning. While parameter names (title, composer, tempo, etc.) are self-explanatory, the description fails to clarify constraints, relationships, or how parameters influence validation. This is a significant gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool validates an input shape without rendering, distinguishing it from the sibling notation_render. It uses specific verbs ('validate') and identifies the resource ('input shape'), making the purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear guidance: 'Cheaper than notation_render — use this when iterating on input shape.' It tells the agent when to use (during iteration) and implies an alternative (notation_render for actual rendering).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
knowledge_search4 fields changedInput schema / properties / limit / descriptionAdded value: +"Maximum chunks to return. Default 8 is right for most queries; raise for broad surveys, lower for tight context budgets."Input schema / properties / maxTokens / descriptionAdded value: +"Token budget for the combined chunk content. Default 1500 fits comfortably in most agent context windows. The endpoint greedy-selects highest-similarity chunks within this budget."Input schema / properties / step / descriptionPrevious value: -"Curriculum step number (1-49) as a fallback if you do not know the topic tag."New value: +"Curriculum step number (1-49). Fallback when you do not know the topic tag. Maps to the Gradus 10-stage curriculum: Stage I 1-7 (single voice, intervals, scales), II 8-13 (counterpoint, all 5 species), III 14-16 (harmony, third voice), IV 17-18 (form, modulation), V 19-20 (fugue), VI 21-25 (classical style, sonata), VII 26-30 (Romantic harmony, augmented sixths), VIII 31-33 (Impressionist), IX 34-36 (20th century), X 37-40 (advanced)."Input schema / properties / topics / descriptionPrevious value: -"Topic tags in kebab-case. Examples: [\"voice-leading\",\"deceptive-cadence\"], [\"chromatic-mediants\"], [\"sonata-form\",\"second-theme\"]."New value: +"Topic tags in kebab-case. Matched semantically via Voyage 3 Large embeddings plus a topic-overlap boost; exact-match is not required, so close synonyms work. Examples: [\"voice-leading\",\"deceptive-cadence\"], [\"chromatic-mediants\"], [\"sonata-form\",\"second-theme\"], [\"figured-bass\",\"6-4-2-chord\"], [\"fugue\",\"stretto\"], [\"modulation\",\"pivot-chord\"]."v0.1.1knowledge_searchnotation_examplesnotation_rendernotation_schemanotation_validateScored across 5 tools
Each tool has a clearly distinct purpose: knowledge_search for theory facts, notation_examples for example inputs, notation_render for rendering, notation_schema for schema retrieval, and notation_validate for input validation. There is no functional overlap.
Tools use a mix of noun_verb (knowledge_search, notation_render, notation_validate) and noun_noun (notation_examples, notation_schema) patterns. Additionally, one tool deviates from the 'notation_' prefix ('knowledge_search'), reducing consistency.
With 5 tools, the server is reasonably scoped for its purpose of music notation rendering and theory knowledge retrieval. It covers core functionality without being overly minimal or excessive.
The tool set covers search, retrieval of examples, input validation, schema access, and rendering. Minor potential gaps (e.g., no tool to list available examples or manage rendered outputs) are not critical for the stated domain.
Turn recordings, videos and sheet music into playable, editable scores. Transcribe audio or video (files or links) to sheet music, read sheet-music photos and PDFs, convert MIDI, MusicXML and ABC, edit notes in conversation with previews and undo, and export PDF, MIDI, MusicXML, guitar TAB, jianpu and audio. Hosted remote server with OAuth sign-in; one instrument, voice or solo piano is free.
Write lyrics in 100+ styles, score them, generate full songs with 4 engines, split stems. OAuth.
Render video and run AI media tasks from a single declarative JSON request.
Deterministic music theory for agents: analyze, voice, reharmonize, conduct — computed, not guessed
