# Samplecut

> Cut audio from YouTube, TikTok or Instagram links to MP3/WAV, and fetch video transcripts.

- name: app.samplecut/samplecut
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 84/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/app.samplecut%2Fsamplecut
- tools: https://api.protogrid.dev/v1/servers/app.samplecut%2Fsamplecut/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "samplecut": {
      "type": "http",
      "url": "https://api.samplecut.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-20d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 84/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: retrim_clip (idempotentHint); cut_audio (idempotentHint); get_transcript (idempotentHint)
- pass `tools.token_cost`: about 1,373 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 7 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 1,373 tokens to load them all
- tool set hash: a24b1fee8d89663e4b6b7379973e6cee
- tools last changed: 2026-10-18T16:46:08.859Z
- badge: [![protogrid quality](https://protogrid.dev/badge/app.samplecut/samplecut.svg)](https://protogrid.dev/servers/app.samplecut/samplecut)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-18 `get_transcript` changed (description, inputSchema)
  - before: Fetch timestamped captions for a YouTube, TikTok, or Instagram 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.
  - after: Fetch timestamped captions for a YouTube, TikTok, Instagram, or SoundCloud 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.
- 2026-10-18 `cut_audio` changed (description, inputSchema)
  - before: Cut audio from a YouTube, TikTok, or Instagram 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.
  - after: Cut audio from a YouTube, TikTok, Instagram, or SoundCloud 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.
- 2026-10-13 `retrim_clip` changed (inputSchema)
- 2026-10-13 `get_transcript` changed (inputSchema)
- 2026-10-13 `cut_audio` changed (inputSchema)
- 2026-09-30 `retrim_clip` added
  - 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.
- 2026-09-30 `cut_audio` changed (description, outputSchema)
  - before: Cut audio from a YouTube, TikTok, or Instagram 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).
  - after: Cut audio from a YouTube, TikTok, or Instagram 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.

Full history: https://api.protogrid.dev/v1/servers/app.samplecut%2Fsamplecut/changes

## Remotes

- https://api.samplecut.app/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (3)

- `cut_audio`: Cut audio from a YouTube, TikTok, Instagram, or SoundCloud 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.
- `get_transcript`: Fetch timestamped captions for a YouTube, TikTok, Instagram, or SoundCloud 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.
- `retrim_clip`: 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.