Skip to main content
Glama

Create a clip request

clipember_create_clip_request

Start a new AI clipping job from a YouTube (or direct video file) URL. Spends 1 credit — check clipember_get_credit_balance first if unsure. Returns immediately with a requestId; the pipeline (transcribe → score → crop → render) usually takes about 5 minutes, and about 1 run in 10 takes 15+ minutes. Call clipember_get_clip_request to check progress — don't poll more than once every 30-60 seconds, and expect to need a fresh call in a LATER turn/message rather than waiting synchronously in this one.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "clipember_create_clip_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoSeconds into the source to stop (max ~1200 = 20 min window)
urlYesYouTube URL or a direct video file URL
genreNoGenre of the video (auto, qa, commentary, marketing, webinar, motivational, podcast, academic, listicle, product_review, howto, comedy, sports, church, news, vlog, gaming, other) — a hint for the moment picker.
startNoSeconds into the source to start processing
promptNoWhich moments to include, in plain words (e.g. 'every moment someone talks about pricing').
seriesNoIf true, make a SERIES: one continuous story from the video split into 2-6 consecutive parts, each ending on a cliffhanger, with 'PART n/N' on screen. Schedule them in order with clipember_schedule_series once rendered.
teaserNoIf true, open each clip with a 1-3 second teaser of its payoff line before the clip starts (a cold open). Not applied to series parts.
lengthsNoClip lengths to look for, several allowed: auto, 0-30s, 30-60s, 60-90s, 90s-3m, 3-5m, 5-10m, 10-15m. Overrides preferredLength.
autoZoomNoAuto zoom: a short punch-in at the end of sentences. On unless false.
captionsNofalse renders the clips without captions.
languageNoSpoken language of the video, ISO 639-1 (e.g. en, uk, es). Default 'auto' detects it from several speech windows across the video; pass it explicitly when the video opens with music or a phrase in another language.auto
watermarkNoBurn a diagonal clipember.com watermark into the rendered clips. Omit to use the account setting (Settings → watermark); pass true/false to override it for this run.
aiKeywordsNoAI keywords: highlight key words in the captions with the style's colors. On unless false.
noClippingNoIf true, render ONE clip of the whole [start,end] range instead of finding multiple highlights
translateToNoCaption language: translate the captions into this language (ISO 639-1); the audio stays original. Omit for the spoken language.
autoHeadlineNoAuto headline: a short title from the clip's hook on the first seconds, away from faces. On unless false.
captionStyleIdNoCaption style of the first render: a preset id (karaoke, bold-pop, rise, notebook, marker, …) or the id of a saved style. Omit for the default look.
preferredLengthNounder60sec

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / aiKeywords
      Added value: +{
      +  "description": "AI keywords: highlight key words in the captions with the style's colors. On unless false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / autoHeadline
      Added value: +{
      +  "description": "Auto headline: a short title from the clip's hook on the first seconds, away from faces. On unless false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / autoZoom
      Added value: +{
      +  "description": "Auto zoom: a short punch-in at the end of sentences. On unless false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / captionStyleId
      Added value: +{
      +  "description": "Caption style of the first render: a preset id (karaoke, bold-pop, rise, notebook, marker, …) or the id of a saved style. Omit for the default look.",
      +  "maxLength": 64,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / captions
      Added value: +{
      +  "description": "false renders the clips without captions.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / genre
      Added value: +{
      +  "description": "Genre of the video (auto, qa, commentary, marketing, webinar, motivational, podcast, academic, listicle, product_review, howto, comedy, sports, church, news, vlog, gaming, other) — a hint for the moment picker.",
      +  "enum": [
      +    "auto",
      +    "qa",
      +    "commentary",
      +    "marketing",
      +    "webinar",
      +    "motivational",
      +    "podcast",
      +    "academic",
      +    "listicle",
      +    "product_review",
      +    "howto",
      +    "comedy",
      +    "sports",
      +    "church",
      +    "news",
      +    "vlog",
      +    "gaming",
      +    "other"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / lengths
      Added value: +{
      +  "description": "Clip lengths to look for, several allowed: auto, 0-30s, 30-60s, 60-90s, 90s-3m, 3-5m, 5-10m, 10-15m. Overrides preferredLength.",
      +  "items": {
      +    "enum": [
      +      "auto",
      +      "0-30s",
      +      "30-60s",
      +      "60-90s",
      +      "90s-3m",
      +      "3-5m",
      +      "5-10m",
      +      "10-15m"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 8,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / prompt
      Added value: +{
      +  "description": "Which moments to include, in plain words (e.g. 'every moment someone talks about pricing').",
      +  "maxLength": 300,
      +  "type": "string"
      +}
    • addedInput schema / properties / translateTo
      Added value: +{
      +  "description": "Caption language: translate the captions into this language (ISO 639-1); the audio stays original. Omit for the spoken language.",
      +  "enum": [
      +    "en",
      +    "uk",
      +    "es",
      +    "pt",
      +    "de",
      +    "fr",
      +    "it",
      +    "pl",
      +    "nl",
      +    "tr",
      +    "ru",
      +    "ar",
      +    "hi",
      +    "id",
      +    "vi",
      +    "ja",
      +    "ko",
      +    "zh"
      +  ],
      +  "type": "string"
      +}
  2. Changed6 schema fields changed
    • addedInput schema / properties / language / anyOf
      Added value: +[
      +  {
      +    "const": "auto",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^[a-z]{2}$",
      +    "type": "string"
      +  }
      +]
    • changedInput schema / properties / language / default
      Previous value: -"en"New value: +"auto"
    • changedInput schema / properties / language / description
      Previous value: -"Source language, ISO 639-1"New value: +"Spoken language of the video, ISO 639-1 (e.g. en, uk, es). Default 'auto' detects it from several speech windows across the video; pass it explicitly when the video opens with music or a phrase in another language."
    • removedInput schema / properties / language / maxLength
      Removed value: -2
    • removedInput schema / properties / language / minLength
      Removed value: -2
    • removedInput schema / properties / language / type
      Removed value: -"string"
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes far beyond annotations by disclosing the cost (1 credit), the multi-stage asynchronous pipeline (transcribe -> score -> crop -> render), and the variability of execution time. This is critical operational context for an AI agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly efficient, using four sentences to cover the core function, cost, process timeline, and required workflow (polling). The information is front-loaded and logically structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high number of parameters (18) and the complexity of an asynchronous, credit-consuming process, the description is complete. It manages all necessary user expectations regarding latency and next steps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

While the input schema is highly detailed, the description adds important semantic context, specifically clarifying that the 'url' parameter supports both YouTube and direct video file formats. It also defines the overall process which applies to how parameters like 'lengths' and 'prompt' should be interpreted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The purpose is explicitly stated as starting a new AI clipping job from a video URL. This is immediately clear and distinct from related operations like listing or editing requests.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The definition provides comprehensive usage guidelines by advising the use of `clipember_get_clip_request` for status checks, warning against synchronous waiting, and giving specific polling frequency limits.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources