@amazon-devices/amazon-devices-buildertools-mcp 0.1.26 → 0.1.30
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.ja.md +55 -4
- package/README.md +112 -5
- package/dist/assets/vega-developer-context.db +0 -0
- package/dist/startserver +5 -5
- package/package.json +1 -1
package/README.ja.md
CHANGED
|
@@ -22,6 +22,10 @@ Amazon Devices Builder Tools MCPは以下の機能をサポートしています
|
|
|
22
22
|
| **フォーカス管理** | TVインターフェース用のD-Padナビゲーションとフォーカス管理を実装 | <ul><li>`フォーカス管理を示すために2つのボタンを持つアプリを作成できますか?`</li></ul> |
|
|
23
23
|
| **SDK & CLI** | SDKのインストール/更新と、仕様駆動型CLIを介した効率的なCLIツールの実行 | <ul><li>`AIエージェントからSDKをインストール/更新`</li><li>`アプリをビルド`</li><li>`仮想デバイスでアプリを実行`</li><li>`物理デバイスでアプリを実行`</li><li>`KPI Visualizerを実行してパフォーマンス結果を取得`</li></ul> |
|
|
24
24
|
| **クラッシュ分析** | JavaScript、Native、LMK、ANRクラッシュの自動ACR分析による診断 | <ul><li>`なぜアプリがクラッシュしたのですか?`</li><li>`このACRファイルを分析してください /path/to/crash.acr`</li></ul> |
|
|
25
|
+
| **キー入力レイテンシー** | JSスレッドパフォーマンスと入力イベント分析によるキー入力レイテンシーの問題を診断・解決 | <ul><li>`なぜアプリのキー入力が遅いのですか?`</li><li>`Vegaアプリのキー入力レイテンシーを診断してください`</li><li>`ボタンクリックが遅く感じます、助けてください`</li></ul> |
|
|
26
|
+
| **UI流暢性** | コンポーネント再レンダリングとCPUパフォーマンス分析によるUI流暢性KPI障害の診断 | <ul><li>`アプリのUI流暢性スコアが低いです、診断してください`</li><li>`Vegaアプリのフレームドロップとジャンクを修正してください`</li><li>`アプリのスクロールがスムーズでないのはなぜですか?`</li></ul> |
|
|
27
|
+
| **アプリ移行** | 視覚的・機能的一貫性を維持しながらFireOS WebViewアプリをVega WebViewアプリに変換 | <ul><li>`FOS WebViewアプリをVega Webアプリに変換してください`</li><li>`/path/to/fos-appにあるFireOS Webアプリをvegaに移行してください`</li></ul> |
|
|
28
|
+
| **Appstore IAP統合** | VegaアプリでAmazon Appstoreアプリ内課金(IAP)SDKを統合・テスト | <ul><li>`VegaアプリにIAPを統合してください`</li><li>`Vegaアプリのアプリ内課金をセットアップするにはどうすればよいですか?`</li><li>`VegaアプリでIAPをテストしてください`</li></ul> |
|
|
25
29
|
| **フィードバックの提供** | MCPの使用体験についてAmazonにフィードバックを提供 | <ul><li>`フィードバックを提供したい`</li><li>`Vega MCPのフィードバックを提供するにはどうすればよいですか?`</li></ul> |
|
|
26
30
|
|
|
27
31
|
## ワンクリックインストール
|
|
@@ -36,10 +40,6 @@ Amazon Devices Builder Tools MCPは以下の機能をサポートしています
|
|
|
36
40
|
|
|
37
41
|
[](https://cursor.com/en-US/install-mcp?name=amazon-devices-buildertools-mcp&config=eyJjb21tYW5kIjoibnB4IC15IEBhbWF6b24tZGV2aWNlcy9hbWF6b24tZGV2aWNlcy1idWlsZGVydG9vbHMtbWNwQGxhdGVzdCJ9)
|
|
38
42
|
|
|
39
|
-
### VSCodeにMCPをインストール
|
|
40
|
-
|
|
41
|
-
[Add to VSCode](vscode:mcp/install?%7B%22name%22%3A%22amazon-devices-buildertools-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40amazon-devices%2Famazon-devices-buildertools-mcp%40latest%22%5D%7D)
|
|
42
|
-
|
|
43
43
|
|
|
44
44
|
## スクリプトによるインストール
|
|
45
45
|
|
|
@@ -229,6 +229,10 @@ Amazon Devices Builder Tools MCPが提供するツールをリストしてくだ
|
|
|
229
229
|
- analyze_perfetto_traces
|
|
230
230
|
- read_document
|
|
231
231
|
- list_documents
|
|
232
|
+
- diagnose_crash
|
|
233
|
+
- diagnose_key_input_latency
|
|
234
|
+
- diagnose_ui_fluidity
|
|
235
|
+
- convert_fos_webview_to_vega
|
|
232
236
|
|
|
233
237
|
## MCPツール
|
|
234
238
|
|
|
@@ -386,3 +390,50 @@ Amazon Devices Builder Tools MCPは、AIエージェントの`/prompts`でワン
|
|
|
386
390
|
```
|
|
387
391
|
> @diagnose_crash /path/to/crash.acr
|
|
388
392
|
```
|
|
393
|
+
|
|
394
|
+
### 7. `diagnose_key_input_latency`
|
|
395
|
+
|
|
396
|
+
**説明:** JSスレッドパフォーマンス、CPUボトルネック、入力イベント処理の最適化を体系的に分析し、React Native Vegaアプリのキー入力レイテンシーの問題を診断・解決します。
|
|
397
|
+
|
|
398
|
+
**パラメータ:**
|
|
399
|
+
|
|
400
|
+
- `vega_app_package_path`(必須、文字列): Vegaアプリパッケージのルートディレクトリへの絶対パス
|
|
401
|
+
- `app_process_name`(任意、文字列): 入力レイテンシーが発生しているアプリプロセスの名前。指定しない場合、manifest.tomlから自動的に解決されます。
|
|
402
|
+
- `perfetto_trace_file_path`(任意、文字列): 既存のPerfettoトレースファイルへの絶対パス(既にキャプチャ済みの場合)
|
|
403
|
+
- `target_component_or_button`(任意、文字列): 調査する特定のボタンまたはコンポーネント名
|
|
404
|
+
- `latency_threshold_ms`(任意、数値): 許容される最大入力レイテンシー(ミリ秒)。デフォルトは100。
|
|
405
|
+
|
|
406
|
+
**使用例:**
|
|
407
|
+
|
|
408
|
+
```
|
|
409
|
+
> @diagnose_key_input_latency /path/to/my-vega-app
|
|
410
|
+
```
|
|
411
|
+
|
|
412
|
+
### 8. `diagnose_ui_fluidity`
|
|
413
|
+
|
|
414
|
+
**説明:** コンポーネント再レンダリングとCPUパフォーマンスボトルネックの体系的な分析を通じて、React Native VegaアプリのUI流暢性KPI障害を診断します。
|
|
415
|
+
|
|
416
|
+
**パラメータ:**
|
|
417
|
+
|
|
418
|
+
- `vega_app_package_path`(必須、文字列): Vegaアプリパッケージのルートディレクトリへの絶対パス
|
|
419
|
+
|
|
420
|
+
**使用例:**
|
|
421
|
+
|
|
422
|
+
```
|
|
423
|
+
> @diagnose_ui_fluidity /path/to/my-vega-app
|
|
424
|
+
```
|
|
425
|
+
|
|
426
|
+
### 9. `convert_fos_webview_to_vega`
|
|
427
|
+
|
|
428
|
+
**説明:** VegaのWebViewコンポーネントを使用して、視覚的・機能的一貫性を維持しながら、既存のFireOS WebViewアプリケーションをVega WebViewアプリケーションに変換します。
|
|
429
|
+
|
|
430
|
+
**パラメータ:**
|
|
431
|
+
|
|
432
|
+
- `fos_app_workspace_path`(必須、文字列): FireOS Webアプリのソースコードへのパス
|
|
433
|
+
- `vega_app_workspace_path`(必須、文字列): Vegaアプリを作成するパス
|
|
434
|
+
|
|
435
|
+
**使用例:**
|
|
436
|
+
|
|
437
|
+
```
|
|
438
|
+
> @convert_fos_webview_to_vega /path/to/fos-web-app /path/to/vega-app
|
|
439
|
+
```
|
package/README.md
CHANGED
|
@@ -22,6 +22,10 @@ The Amazon Devices Builder Tools MCP supports the following capabilities:
|
|
|
22
22
|
| **Focus Management** | Implement D-Pad navigation and focus management for TV interfaces | <ul><li>`Can you create an app with 2 buttons to show case focus management?`</li></ul> |
|
|
23
23
|
| **Give Feedback** | Provide feedback to Amazon about your experience with the MCP | <ul><li>`I want to provide feedback`</li><li>`How can I provide vega mcp feedback?`</li></ul> |
|
|
24
24
|
| **Crash Analysis** | Diagnose JavaScript, Native, LMK, and ANR crashes with automated ACR analysis | <ul><li>`Why did my app crash?`</li><li>`Help me analyze this ACR file /path/to/crash.acr`</li></ul> |
|
|
25
|
+
| **Key Input Latency** | Diagnose and resolve key input latency issues through JS Thread performance and input event analysis | <ul><li>`Why is my app responding slowly to key presses?`</li><li>`Help me diagnose key input latency in my Vega app`</li><li>`My button clicks feel laggy, can you help?`</li></ul> |
|
|
26
|
+
| **UI Fluidity** | Diagnose UI fluidity KPI failures through component re-rendering and CPU performance analysis | <ul><li>`My app's UI fluidity score is low, help me diagnose it`</li><li>`Help me fix frame drops and jank in my Vega app`</li><li>`Why is scrolling not smooth in my app?`</li></ul> |
|
|
27
|
+
| **App Migration** | Convert FireOS WebView apps to Vega WebView apps while maintaining visual and functional consistency | <ul><li>`Convert my FOS WebView app to a Vega Web App`</li><li>`Help me migrate my FireOS web app at /path/to/fos-app to Vega`</li></ul> |
|
|
28
|
+
| **Appstore IAP Integration** | Integrate and test Amazon Appstore In-App Purchasing (IAP) SDK in Vega apps | <ul><li>`Help me integrate IAP in my Vega app`</li><li>`How do I set up In-App Purchasing for my Vega app?`</li><li>`Help me test IAP in my Vega app`</li></ul> |
|
|
25
29
|
| **SDK & CLI** | Install/update SDK and efficiently run CLI tools via spec-driven CLI | <ul><li>`Install/update SDK from AI agents`</li><li>`Build my app`</li><li>`Run my app on virtual device`</li><li>`Run my app on physical device`</li><li>`Run KPI Visualizer and get performance results`</li></ul> |
|
|
26
30
|
|
|
27
31
|
## One-Click Installation
|
|
@@ -36,10 +40,6 @@ Some of the popular AI Agents support installing MCP servers with a single click
|
|
|
36
40
|
|
|
37
41
|
[](https://cursor.com/en-US/install-mcp?name=amazon-devices-buildertools-mcp&config=eyJjb21tYW5kIjoibnB4IC15IEBhbWF6b24tZGV2aWNlcy9hbWF6b24tZGV2aWNlcy1idWlsZGVydG9vbHMtbWNwQGxhdGVzdCJ9)
|
|
38
42
|
|
|
39
|
-
### Install MCP on VSCode
|
|
40
|
-
|
|
41
|
-
[Add to VSCode](vscode:mcp/install?%7B%22name%22%3A%22amazon-devices-buildertools-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40amazon-devices%2Famazon-devices-buildertools-mcp%40latest%22%5D%7D)
|
|
42
|
-
|
|
43
43
|
## Installation with script
|
|
44
44
|
|
|
45
45
|
Run the following command to **automatically** install Amazon Devices Builder Tools MCP in your AI Agent and add Vega-specific context document to your project to guide AI agents:
|
|
@@ -234,7 +234,14 @@ You should see a response that includes the following tools:
|
|
|
234
234
|
- get_app_hot_functions
|
|
235
235
|
- read_document
|
|
236
236
|
- list_documents
|
|
237
|
+
- search_documentation
|
|
238
|
+
- execute_query
|
|
239
|
+
- get_database_schema
|
|
237
240
|
- read_asset
|
|
241
|
+
- diagnose_crash
|
|
242
|
+
- diagnose_key_input_latency
|
|
243
|
+
- diagnose_ui_fluidity
|
|
244
|
+
- convert_fos_webview_to_vega
|
|
238
245
|
|
|
239
246
|
## MCP Tools
|
|
240
247
|
|
|
@@ -318,7 +325,60 @@ or with time window filtering:
|
|
|
318
325
|
Analyze hot functions in /path/to/trace.json from 5 to 15 seconds with a limit of 20 functions
|
|
319
326
|
```
|
|
320
327
|
|
|
321
|
-
### 5. `
|
|
328
|
+
### 5. `search_documentation`
|
|
329
|
+
|
|
330
|
+
Search Vega development documentation using full-text search. Returns document IDs and relevant snippets matching the query. Use `read_document` with the returned ID to get full content.
|
|
331
|
+
|
|
332
|
+
**Parameters:**
|
|
333
|
+
|
|
334
|
+
- `query` (required): Search query string to find relevant documents
|
|
335
|
+
- `snippet_tokens` (optional): Maximum tokens in returned snippets (default: 32)
|
|
336
|
+
|
|
337
|
+
**Example usage:**
|
|
338
|
+
|
|
339
|
+
```
|
|
340
|
+
Search for documents about "performance optimization"
|
|
341
|
+
```
|
|
342
|
+
|
|
343
|
+
or with custom snippet length:
|
|
344
|
+
|
|
345
|
+
```
|
|
346
|
+
Search for "React Native best practices" with 64 token snippets
|
|
347
|
+
```
|
|
348
|
+
|
|
349
|
+
### 6. `get_database_schema`
|
|
350
|
+
|
|
351
|
+
Get the schema for the Vega documentation database. Call this before using `execute_query` to understand available tables, columns, and FTS5 syntax.
|
|
352
|
+
|
|
353
|
+
**Parameters:** None
|
|
354
|
+
|
|
355
|
+
**Example usage:**
|
|
356
|
+
|
|
357
|
+
```
|
|
358
|
+
Get the database schema for Vega documentation
|
|
359
|
+
```
|
|
360
|
+
|
|
361
|
+
### 7. `execute_query`
|
|
362
|
+
|
|
363
|
+
Execute a SQL query against the Vega documentation database. Use this tool for more complex queries when `search_documentation` is insufficient. Use `get_database_schema` first to understand available tables and FTS5 syntax. The database is read-only.
|
|
364
|
+
|
|
365
|
+
**Parameters:**
|
|
366
|
+
|
|
367
|
+
- `sql_query` (required): SQL query to execute against the documentation database
|
|
368
|
+
|
|
369
|
+
**Example usage:**
|
|
370
|
+
|
|
371
|
+
```
|
|
372
|
+
Execute query to search for "performance OR optimization" with custom snippets
|
|
373
|
+
```
|
|
374
|
+
|
|
375
|
+
or with a specific SQL query:
|
|
376
|
+
|
|
377
|
+
```
|
|
378
|
+
Execute query: SELECT dc.id, snippet(document_content_fts, 0, "<b>", "</b>", "...", 64) FROM document_content_fts JOIN document_content dc ON document_content_fts.rowid = dc.rowid WHERE document_content_fts MATCH "performance OR optimization" ORDER BY rank LIMIT 10
|
|
379
|
+
```
|
|
380
|
+
|
|
381
|
+
### 8. `read_asset`
|
|
322
382
|
|
|
323
383
|
Read assets referenced in Vega documentation. Assets are saved to a temporary location and the path is returned. Images can be viewed with
|
|
324
384
|
`fs_read` and scripts executed with the appropriate interpreter (e.g., `python3`)
|
|
@@ -432,3 +492,50 @@ Amazon Devices Builder Tools MCP provides the following pre-defined prompt templ
|
|
|
432
492
|
```
|
|
433
493
|
> @diagnose_crash /path/to/crash.acr
|
|
434
494
|
```
|
|
495
|
+
|
|
496
|
+
### 7. `diagnose_key_input_latency`
|
|
497
|
+
|
|
498
|
+
**Description:** Diagnose and resolve key input latency issues in React Native Vega apps through systematic analysis of JS Thread performance, CPU bottlenecks, and input event handling optimization.
|
|
499
|
+
|
|
500
|
+
**Parameters:**
|
|
501
|
+
|
|
502
|
+
- `vega_app_package_path` (required, string): Absolute path to the Vega app package root directory
|
|
503
|
+
- `app_process_name` (optional, string): Name of the app process experiencing input latency. If not provided, resolved automatically from manifest.toml.
|
|
504
|
+
- `perfetto_trace_file_path` (optional, string): Absolute path to existing Perfetto trace file (if already captured)
|
|
505
|
+
- `target_component_or_button` (optional, string): Specific button or component name to investigate
|
|
506
|
+
- `latency_threshold_ms` (optional, number): Maximum acceptable input latency in milliseconds. Default is 100.
|
|
507
|
+
|
|
508
|
+
**Example usage:**
|
|
509
|
+
|
|
510
|
+
```
|
|
511
|
+
> @diagnose_key_input_latency /path/to/my-vega-app
|
|
512
|
+
```
|
|
513
|
+
|
|
514
|
+
### 8. `diagnose_ui_fluidity`
|
|
515
|
+
|
|
516
|
+
**Description:** Diagnose UI fluidity KPI failures in React Native Vega apps through systematic analysis of component re-rendering and CPU performance bottlenecks.
|
|
517
|
+
|
|
518
|
+
**Parameters:**
|
|
519
|
+
|
|
520
|
+
- `vega_app_package_path` (required, string): Absolute path to the Vega app package root directory
|
|
521
|
+
|
|
522
|
+
**Example usage:**
|
|
523
|
+
|
|
524
|
+
```
|
|
525
|
+
> @diagnose_ui_fluidity /path/to/my-vega-app
|
|
526
|
+
```
|
|
527
|
+
|
|
528
|
+
### 9. `convert_fos_webview_to_vega`
|
|
529
|
+
|
|
530
|
+
**Description:** Convert an existing FireOS WebView application to a Vega WebView application while maintaining visual and functional consistency using Vega's WebView component.
|
|
531
|
+
|
|
532
|
+
**Parameters:**
|
|
533
|
+
|
|
534
|
+
- `fos_app_workspace_path` (required, string): Path to the FireOS web app source code
|
|
535
|
+
- `vega_app_workspace_path` (required, string): Path where the Vega app should be created
|
|
536
|
+
|
|
537
|
+
**Example usage:**
|
|
538
|
+
|
|
539
|
+
```
|
|
540
|
+
> @convert_fos_webview_to_vega /path/to/fos-web-app /path/to/vega-app
|
|
541
|
+
```
|
|
Binary file
|