Skip to main content
Glama
mutonby

mcp-openshorts

by mutonby
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Hybrid

Process a video into short clips

process_video

Starts clipping a video from a URL: downloads, transcribes, detects viral moments, and renders vertical 9:16 clips. Returns a job ID for polling or webhook.

Instructions

Start clipping a video from its URL. OpenShorts downloads the source itself, transcribes it, finds the most viral moments with AI and renders vertical (9:16) clips. Captions and the AI hook line are burned by default; pass captions=false or auto_hook=false to skip either. Call this directly with the URL the user gave you; do not fetch, search or inspect the URL yourself first (you cannot access the video, and it is not needed). Returns a job_id immediately — the work takes minutes; poll get_job_status or pass webhook_url to be called back. The caller must own the content or hold the rights to process it (confirm_rights).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
layoutsNoOptional extra reframe layouts. 'auto' lets AI pick per video.
captionsNoDefault true: burn word-level captions on every clip. Set false when the source already has subtitles burned in (they would stack) or the user wants clean clips; add_subtitles can still caption a clip later.
auto_hookNoBurn the AI-written hook line (the clip's title) over the first seconds of each clip, as the dashboard does. Default true; set false for clean clips.
upload_idNoInstead of source_url: the id from create_upload after the file was PUT to its upload_url. Use when the user gave you a video file rather than a link.
hook_styleNoLook of the hook text (with auto_hook). Default classic.
source_urlNoPublic video URL, passed through exactly as the user gave it (YouTube watch/short/live URL, a direct video file URL, or a tmpfiles.org link from the create_upload fallback). The server does the downloading. Omit when using upload_id.
webhook_urlNoOptional public HTTPS URL POSTed once when the job finishes or fails.
target_clipsNoHow many clips to aim for. A target, not a guarantee: fewer come back when the material doesn't hold them. Default: the AI decides (usually 2-6).
output_formatNoClip aspect. Default auto (vertical).
confirm_rightsYesMust be true: the user owns the content or has rights to process it.
webhook_secretNoOptional secret; the webhook body is then HMAC-SHA256 signed (X-OpenShorts-Signature).
clip_max_secondsNoMaximum clip length in seconds (default 60). Must be ≥ 5s above the minimum.
clip_min_secondsNoMinimum clip length in seconds (default 15).
force_low_qualityNoSet true to proceed after a needs_confirmation low-resolution warning.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.9/5.0
Behavior5/5

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

Fully discloses the tool's behavior: it returns a job_id immediately, takes minutes, and can notify via webhook on success or failure. It also transparently explains defaults for captions and hooks, plus the force_low_quality override. No annotations were provided, so the description bears the full burden and meets it.

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?

The description is thorough and logically organized, covering input, defaults, async flow, and rights. It is somewhat verbose, with several clauses that could be tightened, but every sentence contributes meaningful detail, so the length is justified given the tool's complexity.

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?

The description provides all necessary context for a complex asynchronous tool: input variants, default behavior, output (job_id), completion mechanisms, and required rights confirmation. Without an output schema, it still covers what the caller should expect. No gaps are apparent.

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

Parameters5/5

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

The description adds significant context beyond the schema: it explains interactions (captions stacking, hook text, target_clips as a non-guarantee, clip length constraints, source_url vs upload_id). With 100% schema coverage already, the description enriches parameter understanding rather than repeating it.

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 description clearly states the action ('Start clipping a video') and identifies the resource (a video from a URL or upload). It differentiates from sibling tools by explicitly covering the asynchronous workflow and alternative input methods, making the tool's purpose unambiguous.

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?

Provides explicit instructions on when to call directly (pass the user's URL without fetching it) and when to use upload_id instead. It also explains the async behavior (poll or webhook) and how to handle low-resolution warnings, giving clear usage guidance.

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

Install Server

Other Tools