Vyexa — video link to short clips
by vyexa.net · remote · no sign-in to list tools · v1.0.0 · published by net.vyexa
Turn a video link into vertical short clips with subtitles: create jobs, poll, get downloads.
4 tools: 1 change things and 3 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things1Claude Code: ask: see these tools
- Only reads3Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http clips https://vyexa.net/mcp --header 'Authorization: <your-authorization>'Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
4 tools
Changes things 1Claude Code: ask
create_clipsStart a job that cuts a video link (YouTube, TikTok, Instagram, Vimeo, Twitch, or a direct file URL) into vertical 9:16 short clips with burned-in subtitles.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "create_clips" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Start a job that cuts a video link (YouTube, TikTok, Instagram, Vimeo, Twitch, or a direct file URL) into vertical 9:16 short clips with burned-in subtitles. Returns a job_id immediately; the job runs for a few minutes — poll get_job until status is "completed" or "partial". num_clips is a maximum, not a guarantee. Uses the account's normal clip balance (free plan included).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 3Claude Code: allow
get_jobStatus of a job created with create_clips: status (pending, processing, completed, partial, failed), progress counters, source info and the list of finished clips with download_url…Reads text others writeNo findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "status" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Status of a job created with create_clips: status (pending, processing, completed, partial, failed), progress counters, source info and the list of finished clips with download_url. Poll every 10–15 seconds. "partial" means some clips are usable.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_optionsAll accepted values for layout, subtitle_style, title_style, font, subtitle_position with "when to choose" hints and recommendations by content type (podcast, gaming, humor…).No findings
Why it is in this group
- The name "get_options" says "get": a word for reading.
Description, as the server wrote it All accepted values for layout, subtitle_style, title_style, font, subtitle_position with "when to choose" hints and recommendations by content type (podcast, gaming, humor…). Call once before create_clips to pick styling.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_clipsOnly the finished clips of a job (id, title, duration, download_url).Reads text others writeNo findings
Why it is in this group
- The name "list_clips" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Only the finished clips of a job (id, title, duration, download_url). Each download_url requires the same Bearer key.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http clips https://vyexa.net/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__clips__get_job",
"mcp__clips__list_clips",
"mcp__clips__get_options"
],
"ask": [
"mcp__clips__create_clips"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as clips. Review it before you use it.
Capability tags behind 3 rules
- mcp__clips__create_clips untrusted-input, outbound
- mcp__clips__get_job untrusted-input
- mcp__clips__list_clips untrusted-input