Server definition
- Hash
- sha256:53144c32c6a86635f8ff1a599e56ad7ad5e5ccfee3d9a22c3312def1428b984b
- What it is
- What a remote MCP server returned when asked what it offers: 6 tools
The blob, as servednamed by its sha256
{
"instructions": "gimmeclip downloads public videos from YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo, Twitch, Kick. Use get_video_info to see what a link holds, download_video for an MP4/MP3/GIF file link, get_transcript for AI-readable speech transcripts, share_video for a watch link to send to someone (optionally trimmed with start/end), and edit_video for a vertical or square, captioned clip of up to 60 s. Only public videos, up to 1 GB. Videos up to 2 hours download whole; longer ones, up to 48 hours (Twitch and Kick broadcasts), only give parts of up to 10 minutes: pass both start and end. Long jobs return a job_id or edit_id: call the same tool again with it (check_download for downloads).",
"tools": [
{
"description": "Wait for a download started by download_video and return its link when ready.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"job_id": {
"description": "job_id from download_video.",
"type": "string"
}
},
"required": [
"job_id"
],
"type": "object"
},
"name": "check_download",
"outputSchema": null
},
{
"description": "Prepare a video as MP4 (H.264 + AAC, plays everywhere), MP3, or a looping GIF of up to 10 s, and return a download link. The link works for 15 minutes after the last request. Long videos may still be preparing when this returns: then call check_download with the job_id. Counts against the caller's daily limit (40 per IP).",
"inputSchema": {
"additionalProperties": false,
"properties": {
"end": {
"description": "Optional: end of the part to keep, in seconds (after start).",
"minimum": 0,
"type": "number"
},
"item": {
"default": 1,
"description": "Which video of a multi-video post (1-based); see get_video_info.",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"quality": {
"default": "720",
"description": "Resolution cap (the smaller side, so vertical videos count the same). \"audio\" gives an MP3; \"gif\" a looping GIF of a selection up to 10 s (set start and end).",
"enum": [
"1080",
"720",
"480",
"360",
"audio",
"gif"
],
"type": "string"
},
"start": {
"description": "Optional: start of the part to keep, in seconds.",
"minimum": 0,
"type": "number"
},
"url": {
"description": "Link to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo, Twitch, Kick).",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "download_video",
"outputSchema": null
},
{
"description": "Make an edited copy of part of a public video (up to 60 s between start and end): vertical 9:16 or square crop, burned-in captions of the speech and of other sounds such as \"[dog barking]\" (in the language spoken, or translated to English, Portuguese, Spanish), even loudness; with a prompt also AI-written text over the picture (thought bubbles, meme captions, a title), a dramatic zoom, and slow motion or speed-up. Describe the edit in prompt, or set frame and captions_language (these override the prompt). Returns a gimmeclip.com/w/… watch link kept for 30 days; if it returns an edit_id, call edit_video again with only that edit_id to keep waiting. Each new edit counts against the caller's 30 edits a day, and preparing the source against the daily download limit; repeating the same edit is free.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"captions_language": {
"description": "Burn in captions: \"source\" in the language spoken, or translated. Omit for no captions (unless the prompt asks for them).",
"enum": [
"source",
"en",
"pt",
"es"
],
"type": "string"
},
"edit_id": {
"description": "Only to resume: edit_id from an earlier edit_video call that was still working.",
"type": "string"
},
"end": {
"description": "Optional: end of the part to keep, in seconds (after start).",
"minimum": 0,
"type": "number"
},
"frame": {
"description": "\"9:16\" vertical (default), \"1:1\" square or \"original\".",
"enum": [
"original",
"9:16",
"1:1"
],
"type": "string"
},
"item": {
"default": 1,
"description": "Which video of a multi-video post (1-based); see get_video_info.",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"prompt": {
"description": "Optional: the edit in plain words, e.g. \"15-second vertical with Portuguese captions\".",
"maxLength": 500,
"type": "string"
},
"start": {
"description": "Optional: start of the part to keep, in seconds.",
"minimum": 0,
"type": "number"
},
"url": {
"description": "Link to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo, Twitch, Kick).",
"type": "string"
}
},
"type": "object"
},
"name": "edit_video",
"outputSchema": null
},
{
"description": "Transcribe speech from a public video, optionally between start and end. Returns a transcript_id while processing in the background: call this tool again with transcript_id to check. When done, fetch text_url for timestamped plain text with source attribution; Markdown and JSON links are also provided. Parts without speech are listed as machine-labelled sounds with times, closed-caption style (e.g. \"[cat meowing]\", \"[music]\"). Visual content is not described. New transcription uses the normal daily quota; results last 30 days.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"end": {
"description": "Optional: end of the part to keep, in seconds (after start).",
"minimum": 0,
"type": "number"
},
"item": {
"default": 1,
"description": "Which video of a multi-video post (1-based); see get_video_info.",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"start": {
"description": "Optional: start of the part to keep, in seconds.",
"minimum": 0,
"type": "number"
},
"transcript_id": {
"description": "Resume/check an existing transcription.",
"type": "string"
},
"url": {
"description": "Link to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo, Twitch, Kick).",
"type": "string"
}
},
"type": "object"
},
"name": "get_transcript",
"outputSchema": null
},
{
"description": "Title, uploader, duration, thumbnail and available qualities of a public video link (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo, Twitch, Kick). Posts with several videos list each one as an item.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"url": {
"description": "Link to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo, Twitch, Kick).",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "get_video_info",
"outputSchema": null
},
{
"description": "Prepare the video (or just the part between start and end) and return a short gimmeclip.com/w/… link anyone can open and play, kept for 30 days. Counts against the caller's daily limit (40 per IP, 200 with an API key) unless the same clip was shared before. If it returns a job_id, call share_video again with that job_id to keep waiting.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"end": {
"description": "Optional: end of the part to keep, in seconds (after start).",
"minimum": 0,
"type": "number"
},
"item": {
"default": 1,
"description": "Which video of a multi-video post (1-based); see get_video_info.",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"job_id": {
"description": "Only to resume: job_id from an earlier share_video call that was still preparing.",
"type": "string"
},
"quality": {
"default": "720",
"description": "Resolution cap (the smaller side, so vertical videos count the same).",
"enum": [
"1080",
"720",
"480",
"360"
],
"type": "string"
},
"start": {
"description": "Optional: start of the part to keep, in seconds.",
"minimum": 0,
"type": "number"
},
"url": {
"description": "Link to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo, Twitch, Kick).",
"type": "string"
}
},
"type": "object"
},
"name": "share_video",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:53144c32c6a86635f8ff1a599e56ad7ad5e5ccfee3d9a22c3312def1428b984b | sha256sum