CLIPCLIPER
Timestamped transcripts, chapters and clip suggestions from YouTube, Twitch, Kick or TikTok links.
¿Debería usar esto?
Calidad y seguridad
Hallazgos (2)
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domainen get_transcript
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"clipcliper": {
"url": "https://clipcliper.com/mcp"
}
}
}Puntos de conexión remotos
https://clipcliper.com/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (3)
🟢get_transcript(url, language, format, max_chars, wait_seconds)
Download a public video (YouTube, Twitch VOD, Kick VOD, TikTok) and return its full transcript with timestamps (Whisper large-v3). Asynchronous: if it returns status 'processing', call again with the same url. Results are cached 24 h per url. With a license key it costs one pack minute per started minute of video (minute packs at https://clipcliper.com/mcp; desktop hour packs cost one hour per started hour); without a key, videos up to 15 min (daily limit per IP).
Esquema de entrada
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 8,
"maxLength": 2048,
"description": "Public video URL: YouTube video/short/live replay, Twitch VOD, Kick VOD or TikTok video."
},
"language": {
"description": "Spoken language of the video as ISO-639-1 (e.g. 'en', 'es'). Omit to auto-detect.",
"type": "string",
"pattern": "^[a-z]{2}$"
},
"format": {
"description": "'timestamped' (default, one line per segment: [m:ss] text), 'text' (plain), 'srt' (subtitles) or 'segments' (JSON array of {start,end,text}).",
"type": "string",
"enum": [
"timestamped",
"text",
"srt",
"segments"
]
},
"max_chars": {
"description": "Truncate the transcript to this many characters (default 150000). A 1 h talk is ~50000 chars.",
"type": "integer",
"minimum": 1000,
"maximum": 2000000
},
"wait_seconds": {
"description": "Seconds to wait for processing before returning status 'processing' (default 90). Long videos can take several minutes: just call again.",
"type": "integer",
"minimum": 0,
"maximum": 600
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_chapters(url, max_chapters, language, output_language, wait_seconds)
Split a public video into topic chapters (start/end seconds, title, one-line summary) from its transcript. Transcribes the video first if needed (same cost and async behaviour as get_transcript); the chapters themselves are free and cached.
Esquema de entrada
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 8,
"maxLength": 2048,
"description": "Public video URL: YouTube video/short/live replay, Twitch VOD, Kick VOD or TikTok video."
},
"max_chapters": {
"description": "Upper bound of chapters (default 12).",
"type": "integer",
"minimum": 2,
"maximum": 60
},
"language": {
"description": "Spoken language of the video as ISO-639-1 (e.g. 'en', 'es'). Omit to auto-detect.",
"type": "string",
"pattern": "^[a-z]{2}$"
},
"output_language": {
"description": "Language for titles and summaries (ISO-639-1). Default: the language of the video.",
"type": "string",
"pattern": "^[a-z]{2}$"
},
"wait_seconds": {
"description": "Seconds to wait for processing before returning status 'processing' (default 90). Long videos can take several minutes: just call again.",
"type": "integer",
"minimum": 0,
"maximum": 600
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢suggest_clips(url, count, min_seconds, max_seconds, instruction, ...)
Find the most shareable moments of a public video for short-form clips: start/end seconds aligned to speech, a hook-style title in the video's language and why it works. Transcribes the video first if needed (same cost and async behaviour as get_transcript). Suggestions are free per call.
Esquema de entrada
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 8,
"maxLength": 2048,
"description": "Public video URL: YouTube video/short/live replay, Twitch VOD, Kick VOD or TikTok video."
},
"count": {
"description": "How many clips (default 5; hard cap is one clip per 30 s of video, minimum 20).",
"type": "integer",
"minimum": 1,
"maximum": 600
},
"min_seconds": {
"description": "Shortest clip in seconds (default 20).",
"type": "integer",
"minimum": 3,
"maximum": 590
},
"max_seconds": {
"description": "Longest clip in seconds (default 90).",
"type": "integer",
"minimum": 8,
"maximum": 600
},
"instruction": {
"description": "Editorial guidance, e.g. 'moments about pricing' or 'funny moments only'.",
"type": "string",
"maxLength": 500
},
"language": {
"description": "Spoken language of the video as ISO-639-1 (e.g. 'en', 'es'). Omit to auto-detect.",
"type": "string",
"pattern": "^[a-z]{2}$"
},
"reason_language": {
"description": "Language for the 'reason' field (ISO-639-1, default 'en'). Titles always follow the video's language.",
"type": "string",
"pattern": "^[a-z]{2}$"
},
"wait_seconds": {
"description": "Seconds to wait for processing before returning status 'processing' (default 90). Long videos can take several minutes: just call again.",
"type": "integer",
"minimum": 0,
"maximum": 600
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}Comunidad
Evidencia