The MIDI Analyzer MCP Server is a Model Context Protocol (MCP) server that provides comprehensive tools for loading, parsing, and analyzing Standard MIDI Files (SMF) with extensive filtering capabilities.
Key Capabilities:
Load MIDI Files - Parse MIDI SMF files from specified paths with automatic memory management for efficient repeated access
Get File Summaries - Extract comprehensive information including format type, PPQ (pulses per quarter note), total ticks, track count, tempo, time signatures, and key signatures
Analyze Tracks - List all tracks with optional filtering by MIDI channel (0-15) or program number (0-127), and retrieve detailed track information with metadata
Extract MIDI Events - Retrieve events with advanced filtering by time range (MIDI ticks), event types (noteOn, noteOff, controller, programChange, meta, etc.), specific tracks, and values (note numbers, velocities)
Filter Meta Events - Specifically filter meta events by type such as lyrics, markers, tempo changes, time signatures, and key signatures
Detailed Error Handling - Provides specific error messages for file not found, invalid MIDI files, out-of-range parameters, and other issues
Provides comprehensive tools for analyzing MIDI Standard MIDI Files (SMF), including file parsing, track analysis, event extraction with filtering capabilities, and detailed MIDI data inspection for tempo, time signatures, and musical content.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MIDI Analyzer MCP Server show me the tempo changes in my latest composition.mid"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
標準入力/標準出力でやり取りするシンプルな JSON-RPC 2.0 サーバとして、MIDI (SMF) ファイルの基本的な解析機能を提供します。エージェントや MCP 互換クライアントから「tools/list」「tools/call」を使って呼び出すことを想定しています。
言語: Rust (edition 2024)
ライブラリ: midly, serde, anyhow, tokio など
ファイルの読み込みと識別子 (file_id = sha256) の発行
ファイル全体の概要取得（フォーマット/PPQ/曲尺/テンポ/拍子/キー/トラック統計）
トラック一覧フィルタ（チャンネル/プログラム/インデックス）
トラック詳細（ノートのヒストグラム、CC ヒストグラム要約）
メタ/システムイベント抽出（テンポ/拍子/キー/マーカー/テキスト/SysEx）
すべてのイベントの列挙（ノート、CC、PBEND、プログラムチェンジ、メタ、SysEx）。大量の場合はチャンク単位で取得
Related MCP server: Vibe Composer MIDI MCP
Rust ツールチェーンが必要です（Rustup 推奨）。
ビルド（デバッグ）
Windows: cargo build
生成物: target\debug\midi-analyzer-mcp.exe
ビルド（リリース）
Windows: cargo build --release
生成物: target\release\midi-analyzer-mcp.exe
本プログラムは「1 行に 1 リクエスト JSON」を標準入力で受け取り、1 行の JSON レスポンスを標準出力に書き出します。
リクエスト: { "jsonrpc": "2.0", "id": 任意, "method": "tools/list" | "tools/call", "params": {...} }
レスポンス: { "jsonrpc": "2.0", "id": リクエストの id, "result": ..., "error": ... }
1 行に 1 JSON。複数回呼び出す場合は行ごとに送ります。
利用可能ツール一覧
@'{
"jsonrpc":"2.0",
"id":1,
"method":"tools/list"
}'@ | target\debug\midi-analyzer-mcp.exeファイル概要を取得（パスから直接）
@'{
"jsonrpc":"2.0",
"id":2,
"method":"tools/call",
"params": {
"name":"midi_file_info",
"arguments": { "path": "C:/path/to/song.mid" }
}
}'@ | target\debug\midi-analyzer-mcp.exe先に読み込み（file_id を取得）してから別ツールで使う
@'{
"jsonrpc":"2.0",
"id":3,
"method":"tools/call",
"params": {
"name":"midi_open_file",
"arguments": { "path": "C:/path/to/song.mid", "alias": "main" }
}
}'@ | target\debug\midi-analyzer-mcp.exeレスポンスで返る file_id または alias は後続ツールの file_id として使えます（ただし一部ツールは現在、バイト列が必要なため path 指定が必須です。後述の注意をご参照ください）。
各ツールは params の中で name にツール名、arguments に引数オブジェクトを与えます。
name: midi_open_file
説明: 指定パスの MIDI を読み込み、file_id を返す（後続ツールは file_id を使用可能）
引数: path (必須), alias (任意), validate_extension=true, max_size_bytes=10MB
戻り: { ok, file_id, path, size_bytes, alias }
name: midi_file_info
説明: ファイル全体概要（メタ/テンポ/拍子/キー/曲尺/トラック統計など）
引数: file_id または path のどちらか。include_tempo_map=true, include_time_signatures=true, include_key_signatures=true
戻り: { ok, file_id, format, ppq, duration_ticks, duration_sec, tempo_map, time_signatures, key_signatures, tracks }
name: midi_track_list
説明: トラック一覧（名前/チャンネル/プログラム/ノート統計）
引数: file_id または path。track_indexes[], channel_filter[], program_filter[] など
戻り: { ok, file_id, tracks[] }
name: midi_track_detail
説明: 特定トラック詳細（代表ピッチ/音域/イベント統計、必要に応じてノート/CC 要約）
引数: file_id または path、track_index（必須）。include_histograms=true, include_cc_summary=false
戻り: { ok, file_id, track, pitch_hist(128), cc_hist(128) }
name: midi_system_events
説明: メタ/システムイベントの抽出（テンポ/拍子/キー/マーカー/テキスト/SysEx など）
引数: file_id または path、kinds[]（省略時: tempo, time_signature, key_signature, marker, text, track_name, sysex）、limit, offset
戻り: { ok, file_id, events[], limit, offset, total }
name: midi_all_event
説明: 指定時間範囲のイベント一覧。大量の場合はチャンク分割。
引数:
file_id または path
track_indexes[]（任意）
event_filters: include/exclude/channels/pitches/controllers/programs
time_slice: { start_tick, end_tick }（任意）
chunk_size=2000, chunk_index=0
return_format: "paired_notes" | "flat_events"（デフォルト: paired_notes）
戻り: { ok, file_id, chunk: { index, total }, events[] }
TrackStat
index, name, channels[], programs{ ch->program }, note_count, note_range(min,max), velocity_avg, has_drum
Analyzed
file_id, format, ppq, duration_ticks, duration_sec, tempo_map[(tick,bpm)], time_sigs[(tick,num,den)], key_sigs[(tick,sf,minor)], tracks[]
NoteSpan（paired_notes の要素）
track, chan, pitch, start_tick, end_tick, vel_on, vel_off
FlatEvent（flat_events の要素）
track, tick, sec(現状 None), kind("note_on"/"note_off"/"cc"/"pbend"/"prog"/メタ種別/"sysex"), chan(メタは None), data(JSON)
file_id のみでは「ファイルのバイト列」は保持していません。以下のツールは現状 path が必要です（将来のキャッシュ拡張予定）:
midi_system_events, midi_all_event（file_id だけだとエラーになります）
拍ごとの秒換算（sec）は tempo_map の状況次第で未設定になることがあります。
サポート対象は標準的な SMF。特殊な SysEx 内容などの完全なデコードは行いません（長さのみ）。
parse error（JSON の構文誤り）
method not found（tools/list か tools/call 以外）
unknown tool（不明なツール名）
file not loaded; provide path ...（キャッシュに解析結果が無く、かつ path 未指定）
unsupported extension / file too large / not a file など
解析の中心は src/analyze.rs（midly を用いた基本統計作成）
イベントフィルタは src/filters.rs
モデル定義は src/model.rs
JSON-RPC の I/O とツール実装は src/main.rs
本プロジェクトは MIT ライセンスの下で提供されます。詳細は同梱の LICENSE ファイルをご覧ください。
依存クレート（midly, serde, anyhow, tokio, sha2, base16ct）は MIT または MIT/Apache-2.0 のデュアルライセンスで配布されており、MIT ライセンスとの両立性があります。
Get MIDI events from a file with comprehensive filtering options
| Name | Required | Description | Default |
|---|---|---|---|
| eventTypeFilter | No | Filter events by type | |
| fileId | No | ID of the loaded MIDI file | |
| filePath | No | Path to the MIDI file (if not using fileId) | |
| timeRange | No | Time range to filter events (in MIDI ticks) | |
| trackFilter | No | Filter events by track indexes | |
| valueFilter | No | Filter events by specific values |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'comprehensive filtering options' which hints at functionality, but doesn't describe what the tool returns (e.g., event list format, pagination), error conditions, performance characteristics, or whether it's read-only (though 'Get' implies safe read operation). This leaves significant gaps for a tool with 6 parameters and complex filtering.
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, efficient sentence that front-loads the core purpose. It avoids redundancy and waste, though it could be slightly more structured by explicitly listing key filter types to enhance clarity without adding bulk.
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 (6 parameters with nested objects, no output schema, and no annotations), the description is inadequate. It doesn't explain the return format (e.g., list of events with properties), error handling for invalid filters, or how parameters interact (e.g., fileId vs. filePath). For a data retrieval tool with rich filtering, more context is needed to guide effective use.
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 description coverage is 100%, so the schema already documents all 6 parameters thoroughly. The description adds minimal value beyond the schema by mentioning 'comprehensive filtering options,' which aligns with parameters like eventTypeFilter and timeRange, but doesn't provide additional syntax, format details, or usage examples that aren't already in the parameter descriptions.
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: 'Get MIDI events from a file with comprehensive filtering options.' It specifies the verb ('Get'), resource ('MIDI events'), and scope ('from a file'), but doesn't explicitly differentiate it from sibling tools like get_midi_summary or get_track_details, which likely provide different types of MIDI data.
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 no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like get_midi_summary (which might provide aggregated data) or get_track_details (which might focus on track-level information), leaving the agent to infer usage context from tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get comprehensive summary information about a MIDI file
| Name | Required | Description | Default |
|---|---|---|---|
| fileId | No | ID of the loaded MIDI file | |
| filePath | No | Path to the MIDI file (if not using fileId) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves 'comprehensive summary information,' but fails to specify what that includes (e.g., metadata, track count, duration), whether it's read-only or has side effects, or any constraints like file size limits or authentication needs. This leaves significant gaps in understanding the tool's behavior.
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, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and appropriately sized, with every part contributing to clarity, making it highly concise and well-structured.
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 lack of annotations and output schema, the description is incomplete for a tool with 2 parameters. It doesn't explain what 'comprehensive summary information' entails, such as the structure or content of the return value, nor does it address behavioral aspects like error handling or prerequisites. This leaves the agent with insufficient context for effective use.
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 100% description coverage, clearly documenting both parameters ('fileId' and 'filePath') and their purposes. The description adds no additional parameter information beyond what the schema provides, so it meets the baseline of 3 where the schema does the heavy lifting without compensating for any gaps.
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 action ('Get comprehensive summary information') and resource ('about a MIDI file'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_tracks_list' or 'get_track_details', which might also provide summary-like information about MIDI files.
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?
No guidance is provided on when to use this tool versus alternatives. The description lacks context about how this differs from sibling tools such as 'get_midi_events' or 'get_tracks_list', leaving the agent without explicit usage instructions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about a specific track including events
| Name | Required | Description | Default |
|---|---|---|---|
| eventTypeFilter | No | Filter events by type | |
| fileId | No | ID of the loaded MIDI file | |
| filePath | No | Path to the MIDI file (if not using fileId) | |
| timeRange | No | Time range to filter events (in MIDI ticks) | |
| trackIndex | No | Index of the track to get details for | |
| valueFilter | No | Filter events by specific values |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a 'Get' operation, implying read-only behavior, but doesn't clarify whether it requires specific permissions, what happens with invalid inputs, or the format/structure of the returned information. For a tool with 6 parameters and no output schema, this leaves significant gaps in understanding how it behaves.
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, clear sentence that efficiently communicates the core purpose. There's no wasted language or unnecessary elaboration. It's appropriately sized for what it does communicate, though it could benefit from additional context.
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?
For a tool with 6 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't address what 'detailed information' includes beyond events, doesn't explain the relationship between fileId and filePath parameters, and provides no guidance on error conditions or expected output format. The agent would need to guess about many behavioral aspects.
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 description mentions 'including events' which hints at the event-related parameters, but doesn't add meaningful semantic context beyond what's already in the schema. With 100% schema description coverage, the baseline is 3. The description doesn't explain relationships between parameters (e.g., fileId vs filePath) or provide usage examples that would add value 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: 'Get detailed information about a specific track including events'. It specifies the verb ('Get'), resource ('track'), and scope ('detailed information including events'). However, it doesn't explicitly differentiate from sibling tools like get_midi_events or get_tracks_list, which likely provide overlapping functionality.
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 no guidance on when to use this tool versus alternatives. There are sibling tools like get_midi_events and get_tracks_list that might serve similar purposes, but the description doesn't mention them or explain when this specific tool is appropriate. No context about prerequisites or exclusions is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get list of tracks in a MIDI file with optional filtering by channel or program
| Name | Required | Description | Default |
|---|---|---|---|
| channelFilter | No | Filter tracks by MIDI channel (0-15) | |
| fileId | No | ID of the loaded MIDI file | |
| filePath | No | Path to the MIDI file (if not using fileId) | |
| programFilter | No | Filter tracks by program number (0-127) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions filtering capabilities but doesn't describe what the output looks like (e.g., list format, track properties returned), whether it requires a pre-loaded file (hinted by 'fileId' parameter but not explicitly stated), or any limitations (e.g., file size constraints, error conditions). For a tool with 4 parameters and no output schema, this leaves significant behavioral gaps.
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, efficient sentence that front-loads the core purpose ('Get list of tracks in a MIDI file') followed by the key capability ('with optional filtering by channel or program'). Every word earns its place with zero redundancy or unnecessary elaboration.
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 4 parameters with 100% schema coverage but no annotations and no output schema, the description is adequate but incomplete. It covers the basic purpose and filtering capability but doesn't address important contextual elements like what constitutes a 'track' in MIDI terms, what information is returned about each track, or how this tool relates to the sibling 'load_midi_file' tool (which likely must be called first). The absence of output schema means the description should ideally explain return values, which it doesn't.
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 description coverage is 100%, with all parameters well-documented in the schema itself. The description adds minimal value beyond the schema by mentioning 'optional filtering by channel or program' which corresponds to 'channelFilter' and 'programFilter' parameters. However, it doesn't explain the relationship between 'fileId' and 'filePath' parameters or provide additional context about parameter usage beyond what's already in the schema descriptions.
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 action ('Get list of tracks') and resource ('in a MIDI file'), with specific scope ('with optional filtering by channel or program'). It distinguishes from siblings like 'get_midi_events' or 'get_midi_summary' by focusing on tracks rather than events or overall summary. However, it doesn't explicitly differentiate from 'get_track_details' which might provide more detailed information about individual tracks.
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 implies usage context through 'optional filtering by channel or program', suggesting this tool is for retrieving track lists with specific filters. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'get_track_details' (for detailed track info) or 'get_midi_summary' (for overall file metadata). No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Load and parse a MIDI SMF file from the specified path
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Path to the MIDI file to load |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool loads and parses a file, implying a read operation, but doesn't cover aspects like error handling (e.g., what happens if the file is invalid or missing), performance considerations, or output format. This leaves significant gaps for a tool that interacts with file systems.
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, efficient sentence that directly states the tool's function without unnecessary words. It is front-loaded with the core action and resource, making it easy to understand at a glance.
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 lack of annotations and output schema, the description is incomplete for a file-loading tool. It doesn't explain what the parsed output entails (e.g., structured data or events), error scenarios, or how it integrates with sibling tools, leaving the agent with insufficient context for effective use.
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 schema description coverage is 100%, with the single parameter 'filePath' fully documented in the schema. The description adds no additional meaning beyond what the schema provides, such as file format specifics or path requirements, so it meets the baseline for high schema coverage without compensating value.
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 action ('Load and parse') and resource ('a MIDI SMF file from the specified path'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_midi_events' or 'get_midi_summary' which might also involve loading MIDI files, so it doesn't reach the highest clarity level.
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 no guidance on when to use this tool versus alternatives like the sibling tools listed. It doesn't mention prerequisites, such as needing a valid file path, or specify use cases like initial file loading before accessing events or summaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: load_midi_file handles file loading, get_tracks_list lists tracks, get_track_details provides track-specific details, get_midi_events extracts events with filtering, and get_midi_summary gives overall file information. There is no overlap or ambiguity in functionality.
All tools follow a consistent verb_noun pattern with snake_case naming (e.g., get_midi_events, load_midi_file). The verbs are appropriate and uniform across the set, making the naming highly predictable and readable.
With 5 tools, this server is well-scoped for MIDI file analysis, covering essential operations like loading, listing, detailing, event extraction, and summarization. Each tool earns its place without being excessive or insufficient.
The tool set provides complete coverage for MIDI file analysis: loading files, listing tracks, getting track details, extracting events, and summarizing files. There are no obvious gaps, and the tools support a full workflow from file access to detailed inspection.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Audio features + harmonic set-building for tracks by name/ISRC. Spotify audio-features replacement.
Create, co-edit, analyze, publish, and export collaborative step-sequencer sessions through MCP.
Structured analysis API and remote MCP tool for text, JSON records and numeric series.
Convert projects between Logic, Ableton, FL Studio and REAPER; generate, separate, transcribe
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sin5ddd/midi-analyzer-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
