vlearn
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | No | Path to the vlearn repository so the app.mcp.server module can be imported (e.g. /path/to/vlearn). | |
| VLEARN_CONFIG | No | Path to the vlearn configuration file (e.g. /path/to/vlearn/config/default.yaml). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| import_trend_csvC | 導入短影音熱度 CSV。 |
| list_trend_topC | 按熱度返回前 n 條。 |
| list_videosC | 列出已攝取視頻。 |
| get_videoC | 視頻元數據 + 源片段統計。 |
| get_reportC | 讀取 Markdown 報告。 |
| get_conflictsC | 衝突列表；unresolved 保留雙版本。 |
| preview_keyframe_selectionC | 預覽右邊界截斷結果（幀級精確，本地完整視頻場景）。 |
| preview_keyframe_selection_seekC | 預覽 seek 版的 margin 截斷結果（遠程 seek 場景）。 |
| arbitrate_evidenceC | 對給定證據執行仲裁。summaries: [{source_type, confidence, quality_flags}] |
| get_cost_summaryC | 成本與預算餘量。 |
| submit_correctionD | 提交人工修正。 |
| ingest_videoC | 攝取元數據 + 字幕。 |
| analyze_videoC | 啟動異步分析，返回 job_id。 |
| get_job_statusD | 輪詢 job。 |
| read_frame_atA | 按需讀單幀，返回 [本地 VLM 描述 + 原始圖片] 雙重視角。 include_image 參數（支持字符串形式 "true"/"false"）：
無論 include_image 是 True 還是 False，TextContent 裡始終包含 Qwen3-VL 27B 生成的完整畫面描述 + 提取的斷言。
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_youtube | |
| trend_digest |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
Most tools map to a distinct resource plus action (ingest, analyze, poll job, report, conflicts, cost, correction). The only real overlap is preview_keyframe_selection vs. preview_keyframe_selection_seek, which are near-duplicates split by local vs. remote scenario; the descriptions differentiate them but the boundary requires reading carefully.
Names are overwhelmingly verb-first snake_case (get_report, list_videos, ingest_video, analyze_video, submit_correction, read_frame_at), giving a predictable pattern. Minor deviations: list_trend_top inverts the noun/qualifier order, and import_trend_csv embeds the object, but nothing is genuinely chaotic.
15 tools sit at the top of the well-scoped range and each covers a step in the ingest → analyze → poll → report → correct pipeline, plus trend and cost views. No tool looks redundant except the deliberate preview pair.
The core lifecycle (ingest, async analyze, job polling, report, conflicts, correction) is covered, so no dead end in the main flow. However there is no way to delete or re-ingest a video, list/cancel running jobs, or enumerate available reports, and trend data can only be imported and read as top-n with no query or update path.