clip_video
Cut ONE long video into several RANKED, ready-to-post short clips (podcast, webinar, interview, talk, long ad cut -> Reels/Shorts/TikTok). Transcribes with timestamps, picks the strongest SELF-CONTAINED moments, then cuts + reframes each with ffmpeg — no video model renders anything, so it is fas...
This record as markdown: /tools/hermoso/clip-video.md
What clip_video does on Hermoso
AI agents call clip_video to retrieve information from Hermoso without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why clip_video is rated Low
Even though clip_video only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs clip_video safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hermoso, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For clip_video, this is the rule to start with:
clip_video is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Hermoso, apply this rule, and every clip_video call is checked against it from then on.
Questions about clip_video
Cut ONE long video into several RANKED, ready-to-post short clips (podcast, webinar, interview, talk, long ad cut -> Reels/Shorts/TikTok). Transcribes with timestamps, picks the strongest SELF-CONTAINED moments, then cuts + reframes each with ffmpeg — no video model renders anything, so it is fast and cheap. THE VERTICAL REFRAME IS SUBJECT-AWARE: one cheap vision call per clip (billed as its own event) picks a SINGLE crop offset held for the whole clip, so a speaker sitting camera-left is not cropped out and the framing never drifts inside a clip; with nothing to discard or no single subject it stays dead centre — read. It is categorised as a Read tool in the Hermoso MCP Server, which means it retrieves data without modifying state.
Register the Hermoso MCP server in PolicyLayer and add a rule for clip_video: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Hermoso. Nothing to install.
clip_video is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the clip_video rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for clip_video. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
clip_video is provided by the Hermoso MCP server (https://app.hermoso.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hermoso, and thousands of servers like it.
This server
Across the catalogue