Samplecut is an MCP server published by app.samplecut, hosted at api.samplecut.app. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including cut_audio, get_transcript, retrim_clip, send_feedback.
Cut audio from YouTube, TikTok or Instagram links to MP3/WAV, and fetch video transcripts.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| url * | string | YouTube, TikTok, Instagram, SoundCloud, or X URL to cut |
| format | string | Download format; default mp3 |
| context * | string |
None yet. Changes appear after a server's second daily check.
| 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. |
| end_sec | number | Range end in seconds |
| llm_model * | string | 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. |
| start_sec | number | Range start in seconds |
| duration_sec | number | Clip length in seconds from start_sec (default 0) when end_sec is omitted |
| conversation_id | string | 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 messa… |
{
"name": "cut_audio",
"title": "Cut audio",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"url",
"context",
"llm_model"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube, TikTok, Instagram, SoundCloud, or X URL to cut"
},
"format": {
"enum": [
"wav",
"mp3"
],
"type": "string",
"description": "Download format; default mp3"
},
"context": {
"type": "string",
"description": "One short sentence on what the user is trying to do with this audio (for example 'ringtone from the chorus'). No links, names or personal details."
},
"end_sec": {
"type": "number",
"description": "Range end in seconds",
"exclusiveMinimum": 0
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"start_sec": {
"type": "number",
"minimum": 0,
"description": "Range start in seconds"
},
"duration_sec": {
"type": "number",
"description": "Clip length in seconds from start_sec (default 0) when end_sec is omitted",
"exclusiveMinimum": 0
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"title",
"format",
"full",
"download_url",
"editor_url",
"expires_at",
"clip_id",
"track_duration_sec",
"filename",
"peaks"
],
"properties": {
"full": {
"type": "boolean"
},
"peaks": {
"type": "array",
"items": {
"type": "number"
}
},
"title": {
"type": "string"
},
"format": {
"enum": [
"wav",
"mp3"
],
"type": "string"
},
"clip_id": {
"type": "string"
},
"end_sec": {
"type": "number"
},
"filename": {
"type": "string"
},
"start_sec": {
"type": "number"
},
"editor_url": {
"type": "string"
},
"expires_at": {
"type": "string"
},
"download_url": {
"type": "string"
},
"track_duration_sec": {
"type": "number"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| url * | string | YouTube, TikTok, Instagram, SoundCloud, or X URL to fetch captions for |
| lang | string | Optional BCP-47 caption language (default en) |
| context * | string | 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 * | string | 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 | string | 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 messa… |
{
"name": "get_transcript",
"title": "Get transcript",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"url",
"context",
"llm_model"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube, TikTok, Instagram, SoundCloud, or X URL to fetch captions for"
},
"lang": {
"type": "string",
"maxLength": 32,
"minLength": 1,
"description": "Optional BCP-47 caption language (default en)"
},
"context": {
"type": "string",
"description": "One short sentence on what the user is trying to do with this audio (for example 'ringtone from the chorus'). No links, names or personal details."
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"available",
"source",
"lang",
"segments",
"text"
],
"properties": {
"lang": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"text": {
"type": "string"
},
"source": {
"anyOf": [
{
"enum": [
"youtube_captions"
],
"type": "string"
},
{
"type": "null"
}
]
},
"segments": {
"type": "array",
"items": {
"type": "object",
"required": [
"start_sec",
"end_sec",
"text"
],
"properties": {
"text": {
"type": "string"
},
"end_sec": {
"type": "number"
},
"start_sec": {
"type": "number"
}
},
"additionalProperties": false
}
},
"available": {
"type": "boolean"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| format | string | Download format; default the clip's current format |
| clip_id * | string | clip_id from a cut_audio result |
| context | string | Optional: why the clip is being re-cut |
| end_sec * | number | New range end in seconds |
| llm_model | string | Optional: the model making this call |
| start_sec * | number | New range start in seconds |
| conversation_id | string | 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 messa… |
{
"name": "retrim_clip",
"title": "Adjust clip",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"clip_id",
"start_sec",
"end_sec"
],
"properties": {
"format": {
"enum": [
"wav",
"mp3"
],
"type": "string",
"description": "Download format; default the clip's current format"
},
"clip_id": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "clip_id from a cut_audio result"
},
"context": {
"type": "string",
"description": "Optional: why the clip is being re-cut"
},
"end_sec": {
"type": "number",
"description": "New range end in seconds",
"exclusiveMinimum": 0
},
"llm_model": {
"type": "string",
"description": "Optional: the model making this call"
},
"start_sec": {
"type": "number",
"minimum": 0,
"description": "New range start in seconds"
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"title",
"format",
"full",
"download_url",
"editor_url",
"expires_at",
"clip_id",
"track_duration_sec",
"filename",
"peaks"
],
"properties": {
"full": {
"type": "boolean"
},
"peaks": {
"type": "array",
"items": {
"type": "number"
}
},
"title": {
"type": "string"
},
"format": {
"enum": [
"wav",
"mp3"
],
"type": "string"
},
"clip_id": {
"type": "string"
},
"end_sec": {
"type": "number"
},
"filename": {
"type": "string"
},
"start_sec": {
"type": "number"
},
"editor_url": {
"type": "string"
},
"expires_at": {
"type": "string"
},
"download_url": {
"type": "string"
},
"track_duration_sec": {
"type": "number"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| details | string | 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. |
| summary * | string | 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.' |
| llm_model * | string | 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. |
| sentiment | string | Optional: how the experience felt overall. |
| tool_name | string | Optional: the existing tool this feedback is about (for 'issue' or 'praise'). Leave empty for 'missing_capability' - the point is that no tool fits. |
| feedback_type * | string | 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… |
| task_completed | boolean | Optional: whether you still completed the user's task despite the problem. |
| conversation_id | string | 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 messa… |
| friction_points | string | Optional: the specific moments that slowed you down, as short bullet-like sentences, quoting exact tool names, parameters, or error text. |
| suggested_improvement | string | Optional: the concrete change that would have helped, e.g. the tool to add, the description to reword, or the error message to improve. |
{
"name": "send_feedback",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"feedback_type",
"summary",
"llm_model"
],
"properties": {
"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."
},
"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.'"
},
"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."
},
"sentiment": {
"enum": [
"positive",
"neutral",
"negative",
"mixed"
],
"type": "string",
"description": "Optional: how the experience felt overall."
},
"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."
},
"feedback_type": {
"enum": [
"missing_capability",
"issue",
"praise",
"other"
],
"type": "string",
"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."
},
"task_completed": {
"type": "boolean",
"description": "Optional: whether you still completed the user's task despite the problem."
},
"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."
},
"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."
}
}
},
"annotations": {
"title": "Send feedback",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.