Skip to main content
Glama
miracleweasel

katto-mcp

by miracleweasel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

katto_create_clip_job

Submit a long video by public URL or upload ID to start asynchronous clipping, then poll the job or use a webhook to get scored 9:16 clips.

Instructions

Submit a long video for clipping, either by public link in url (YouTube, Twitch, Kick, Vimeo, Zoom, Google Drive, Dropbox, Loom, LinkedIn, Facebook, Rumble, Dailymotion, Medal.tv, or a direct https link to a video file; Google Drive and Dropbox links must be shared publicly) or, for a local file, by upload_id after katto_upload_video and the PUT of the file. Pass exactly one of url or upload_id. Consumes 1 video from your monthly quota — check katto_get_usage first. Clips are produced asynchronously; returns a job id, then poll katto_get_job every 30-60 s until status is 'completed', or pass webhook_url to be notified (url jobs only). Pass idempotency_key when you might retry a url job, so a retry never spends a second video (an upload can only be started once anyway). Fails if the URL is unsupported, the uploaded file is missing, or the video is longer than your plan allows.

Input Schema

NameRequiredDescriptionDefault
urlNoPublic video URL to clip (YouTube, Twitch, Kick, Vimeo, Zoom, Google Drive, Dropbox, Loom, LinkedIn, Facebook, Rumble, Dailymotion, Medal.tv, or a direct https link to a video file). Pass url OR upload_id.
configNoOptional pre-clip settings.
upload_idNoInstead of url: the upload_id returned by katto_upload_video, once the file has been PUT to its upload_url. Starts clipping that file.
webhook_urlNoOptional https URL that receives a signed POST when the job finishes, so you do not have to poll. Verify the signature with the secret from katto_get_webhook_secret. Private and local addresses are refused.
idempotency_keyNoOptional unique string (max 255 chars). Retrying with the same key returns the original job instead of creating a second one and spending another video. Use one per intended job, e.g. a UUID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv0.6.1
    • addedInput schema / properties / config / properties / clipLength / description
      Added value: +"Target length band for the clips, in seconds. Guides candidate selection by setting a minimum and maximum duration; it is a preference, not a hard cut. Omit to let the model decide."
    • addedInput schema / properties / config / properties / customPrompt / description
      Added value: +"Free-text hint about what matters in this video. Its keywords nudge selection toward matching moments. It does not filter: a clip that matches nothing can still be selected if it scores well."
    • addedInput schema / properties / config / properties / topics / description
      Added value: +"Comma-separated topics to favour. Merged with customPrompt into a single keyword hint, so both bias the ranking rather than restrict it."
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Optional unique string (max 255 chars). Retrying with the same key returns the original job instead of creating a second one and spending another video. Use one per intended job, e.g. a UUID.",
+  "type": "string"
+}
    • addedInput schema / properties / upload_id
      Added value: +{
+  "description": "Instead of url: the upload_id returned by katto_upload_video, once the file has been PUT to its upload_url. Starts clipping that file.",
+  "type": "string"
+}
    • changedInput schema / properties / url / description
      Previous value: -"Public video URL to clip."New value: +"Public video URL to clip (YouTube, Twitch, Kick, Vimeo, Zoom, Google Drive, Dropbox, Loom, LinkedIn, Facebook, Rumble, Dailymotion, Medal.tv, or a direct https link to a video file). Pass url OR upload_id."
    • addedInput schema / properties / webhook_url
      Added value: +{
+  "description": "Optional https URL that receives a signed POST when the job finishes, so you do not have to poll. Verify the signature with the secret from katto_get_webhook_secret. Private and local addresses are refused.",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "url"
-]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only flag readOnly=false, idempotent=false, destructive=false, openWorld=true; the description goes well beyond them by disclosing the quota cost (one video per job), asynchronous job-id return, polling cadence, signed webhook delivery, and the three failure modes. The idempotency_key guidance complements rather than contradicts idempotentHint=false, since it explains how to make a retry safe.

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

Conciseness4/5

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

Front-loaded with the core action and the url/upload_id choice, then layers quota, async behavior, and idempotency in a logical order. It loses a point for re-listing all fourteen supported platforms verbatim when the url parameter already enumerates them.

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?

With no output schema, the description still explains what comes back (a job id), how to observe completion (polling or webhook), and what causes failure, so an agent has everything needed to invoke and follow up correctly.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds constraints the schema does not encode: the url/upload_id exclusivity rule (required is 0, with no oneOf in the schema), the public-sharing requirement for Drive/Dropbox, and that webhook_url works for url jobs only. Nested config fields (genre, topics, clipLength, customPrompt) are left entirely to the schema.

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?

States a specific verb and resource ('Submit a long video for clipping') plus the two mutually exclusive input modes (url vs upload_id), which cleanly separates it from siblings like katto_create_clip and katto_upload_video. An agent knows this is the entry point that starts an async clipping job from a full-length source video.

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?

Gives explicit sequencing and alternatives: check katto_get_usage first, pass exactly one of url/upload_id, then poll katto_get_job every 30-60s or supply webhook_url instead, and use idempotency_key when retrying url jobs. Conditions and the sibling tools to call next are all named rather than left to inference.

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

Deploy Server

Other Tools