mcp-openshorts
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | No | AWS region (default: us-east-1) | us-east-1 |
| AWS_S3_BUCKET | No | Private bucket for clip backup | |
| AWS_ACCESS_KEY_ID | No | AWS access key for S3 | |
| MAX_CONCURRENT_JOBS | No | Concurrent processing limit (default: 5) | 5 |
| AWS_S3_PUBLIC_BUCKET | No | Public bucket for gallery/avatars | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| process_videoA | 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). |
| create_uploadA | Use when the user hands you a video FILE instead of a link. Returns an upload_url: send the file's raw bytes to it with an HTTP PUT (for example |
| get_job_statusA | Status of a processing job: 'queued', 'processing', 'completed' or 'failed', with recent log lines and, once completed, the clips. |
| list_clipsC | The clips of a completed job, with titles, platform-ready descriptions and download URLs. In MCP Apps-capable clients the result also renders as an interactive clip picker. |
| get_quotaA | The authenticated user's plan and remaining processing minutes. Call before large jobs; process_video fails with quota_exceeded when the balance is insufficient. |
| add_subtitlesB | Re-style the captions of one clip (clips already ship with default captions). style 'karaoke' highlights the active word. |
| recut_clipA | Re-render one clip from a new list of source-video segments (the same engine behind the dashboard's clip editor). Times are seconds in the ORIGINAL source video; segments are concatenated in the given order, so you can trim, extend, drop a dead moment in the middle, or reorder. Segments inside the clip's original range re-render in seconds; going outside needs the retained source video and re-runs the reframe engine. |
| publish_clipA | Post one clip to the user's connected accounts (TikTok lands as a draft in the app; Instagram and YouTube publish directly). Requires a connected social profile (cloud) or an Upload-Post key (self-host). Optionally schedule with an ISO-8601 scheduled_date. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| clip-picker | Interactive picker for a job's finished clips: preview each 9:16 clip, select the keepers and publish them to TikTok, Instagram or YouTube without leaving the conversation. |
TDQS
Scored across 8 tools
Each tool has a distinct purpose: quota checking, upload creation, video processing, job status polling, clip listing, subtitle styling, clip recutting, and publishing. No two tools appear to overlap in functionality.
All tool names follow a consistent verb_noun snake_case pattern (e.g., list_clips, get_quota, process_video, publish_clip). The naming is predictable and clear.
With 8 tools, the set is well-scoped for a video clipping service, covering the main workflow from upload/processing through editing and publishing without being bloated.
The tool surface covers the full core lifecycle: create upload, process video, monitor jobs, list clips, edit clips, and publish. Minor gaps like deleting clips or retrieving individual clip details exist but are not critical to the primary workflow.