Samplecut
Cut audio from YouTube, TikTok or Instagram links to MP3/WAV, and fetch video transcripts.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"samplecut": {
"url": "https://api.samplecut.app/mcp"
}
}
}リモートエンドポイント
https://api.samplecut.app/mcpstreamable-httpできること
ツール一覧
ツール(4)
🟢cut_audio(url, start_sec, end_sec, duration_sec, format, ...)
Cut audio from a YouTube, TikTok, Instagram, SoundCloud, or X URL and return a short-lived download link. Lead with download_url for cut/download requests; offer editor_url when the user wants to tweak the selection. Links expire after about an hour — ask again in chat for a fresh cut if expired. Omit start_sec and end_sec for the full track. format defaults to mp3 (wav allowed). clip_id and peaks drive the interactive clip card some chat apps show; do not show them to the user. If the user adjusted the clip in the card, read the widget context for the current range and download link before answering follow-ups.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "YouTube, TikTok, Instagram, SoundCloud, or X URL to cut"
},
"start_sec": {
"description": "Range start in seconds",
"type": "number",
"minimum": 0
},
"end_sec": {
"description": "Range end in seconds",
"type": "number",
"exclusiveMinimum": 0
},
"duration_sec": {
"description": "Clip length in seconds from start_sec (default 0) when end_sec is omitted",
"type": "number",
"exclusiveMinimum": 0
},
"format": {
"description": "Download format; default mp3",
"type": "string",
"enum": [
"wav",
"mp3"
]
},
"context": {
"type": "string",
"description": "One short sentence on what the user is trying to do with this audio (for example 'ringtone from the chorus'). No links, names or personal details."
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"url",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"title": {
"type": "string"
},
"format": {
"type": "string",
"enum": [
"wav",
"mp3"
]
},
"full": {
"type": "boolean"
},
"download_url": {
"type": "string"
},
"editor_url": {
"type": "string"
},
"expires_at": {
"type": "string"
},
"start_sec": {
"type": "number"
},
"end_sec": {
"type": "number"
},
"clip_id": {
"type": "string"
},
"track_duration_sec": {
"type": "number"
},
"filename": {
"type": "string"
},
"peaks": {
"type": "array",
"items": {
"type": "number"
}
}
},
"required": [
"title",
"format",
"full",
"download_url",
"editor_url",
"expires_at",
"clip_id",
"track_duration_sec",
"filename",
"peaks"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_transcript(url, lang, context, llm_model, conversation_id)
Fetch timestamped captions for a YouTube, TikTok, Instagram, SoundCloud, or X URL when the platform provides them. Use segment start_sec/end_sec (or the flat text) to choose a cut range, then call cut_audio with the same URL and those times. When available is false there are no captions — do not invent lyrics or timestamps; tell the user to pick times another way. Optional lang is a BCP-47 code (default en). No job_id is returned.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "YouTube, TikTok, Instagram, SoundCloud, or X URL to fetch captions for"
},
"lang": {
"description": "Optional BCP-47 caption language (default en)",
"type": "string",
"minLength": 1,
"maxLength": 32
},
"context": {
"type": "string",
"description": "One short sentence on what the user is trying to do with this audio (for example 'ringtone from the chorus'). No links, names or personal details."
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"url",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"available": {
"type": "boolean"
},
"source": {
"anyOf": [
{
"type": "string",
"enum": [
"youtube_captions"
]
},
{
"type": "null"
}
]
},
"lang": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"segments": {
"type": "array",
"items": {
"type": "object",
"properties": {
"start_sec": {
"type": "number"
},
"end_sec": {
"type": "number"
},
"text": {
"type": "string"
}
},
"required": [
"start_sec",
"end_sec",
"text"
],
"additionalProperties": false
}
},
"text": {
"type": "string"
}
},
"required": [
"available",
"source",
"lang",
"segments",
"text"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}⚪retrim_clip(clip_id, start_sec, end_sec, format, context, ...)
Re-cut a clip from Samplecut's clip card to a new start/end, reusing the audio already extracted for it. Called by the interactive card; to cut something new, use cut_audio.
入力スキーマ
{
"type": "object",
"properties": {
"clip_id": {
"type": "string",
"minLength": 1,
"maxLength": 64,
"description": "clip_id from a cut_audio result"
},
"start_sec": {
"type": "number",
"minimum": 0,
"description": "New range start in seconds"
},
"end_sec": {
"type": "number",
"exclusiveMinimum": 0,
"description": "New range end in seconds"
},
"format": {
"description": "Download format; default the clip's current format",
"type": "string",
"enum": [
"wav",
"mp3"
]
},
"context": {
"description": "Optional: why the clip is being re-cut",
"type": "string"
},
"llm_model": {
"description": "Optional: the model making this call",
"type": "string"
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"clip_id",
"start_sec",
"end_sec"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"title": {
"type": "string"
},
"format": {
"type": "string",
"enum": [
"wav",
"mp3"
]
},
"full": {
"type": "boolean"
},
"download_url": {
"type": "string"
},
"editor_url": {
"type": "string"
},
"expires_at": {
"type": "string"
},
"start_sec": {
"type": "number"
},
"end_sec": {
"type": "number"
},
"clip_id": {
"type": "string"
},
"track_duration_sec": {
"type": "number"
},
"filename": {
"type": "string"
},
"peaks": {
"type": "array",
"items": {
"type": "number"
}
}
},
"required": [
"title",
"format",
"full",
"download_url",
"editor_url",
"expires_at",
"clip_id",
"track_duration_sec",
"filename",
"peaks"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢send_feedback(feedback_type, summary, details, friction_points, suggested_improvement, ...)
Tell Samplecut's developers how the user's task went. Call it once after you finish or give up on a task where you used these tools, with task_completed set to whether the user got what they wanted. Use feedback_type "missing_capability" when the goal needed something these tools do not do (for example naming a song or separating vocals), even if you finished it another way; "issue" when a tool failed, or its result was wrong or confusing; "praise" when it went well. This only records feedback. No links, names or personal details.
入力スキーマ
{
"type": "object",
"properties": {
"feedback_type": {
"type": "string",
"enum": [
"missing_capability",
"issue",
"praise",
"other"
],
"description": "What kind of feedback this is. Use 'missing_capability' when the tool you needed does not exist in the tool list - nothing failed, the capability is absent (this is the most valuable report; send it even if you found a workaround). Use 'issue' when an existing tool behaved badly: it failed, returned a confusing error, or its description or schema misled you. Use 'praise' when something worked notably well. Use 'other' for anything else."
},
"summary": {
"type": "string",
"description": "One self-contained sentence. For 'missing_capability': the capability you needed, e.g. 'No tool to delete multiple cohorts in one call.' For 'issue': the tool and the problem, e.g. 'query-trends rejects relative date ranges with an unclear error.'"
},
"details": {
"type": "string",
"description": "Optional longer context: what you tried, exact parameter values, the error text you saw, and any workaround you used. Omit when the summary says it all."
},
"friction_points": {
"type": "string",
"description": "Optional: the specific moments that slowed you down, as short bullet-like sentences, quoting exact tool names, parameters, or error text."
},
"suggested_improvement": {
"type": "string",
"description": "Optional: the concrete change that would have helped, e.g. the tool to add, the description to reword, or the error message to improve."
},
"tool_name": {
"type": "string",
"description": "Optional: the existing tool this feedback is about (for 'issue' or 'praise'). Leave empty for 'missing_capability' - the point is that no tool fits."
},
"sentiment": {
"type": "string",
"enum": [
"positive",
"neutral",
"negative",
"mixed"
],
"description": "Optional: how the experience felt overall."
},
"task_completed": {
"type": "boolean",
"description": "Optional: whether you still completed the user's task despite the problem."
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"feedback_type",
"summary",
"llm_model"
]
}コミュニティ
エビデンス