render_edit_plan
Render a CutPilot JSON project to a local MP4 using FFmpeg.
This record as markdown: /tools/cutpilot/render-edit-plan.md
What render_edit_plan does on Cutpilot
AI agents invoke render_edit_plan to trigger actions in Cutpilot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why render_edit_plan is rated High
This tool executes FFmpeg, an external process, to render video content. It triggers a real computational operation with side effects (writing an MP4 file to disk). While it also involves writing, the dominant characteristic is executing an external program (FFmpeg) whose behavior depends on the input project JSON. Misuse could consume significant system resources, overwrite files, or produce unintended video output.
From the tool's definition "Render a CutPilot JSON project to a local MP4 using FFmpeg"
Attacks that exploit this kind of access
The rule that runs render_edit_plan safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cutpilot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For render_edit_plan, this is the rule to start with:
render_edit_plan stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cutpilot, apply this rule, and every render_edit_plan call is checked against it from then on.
Questions about render_edit_plan
Render a CutPilot JSON project to a local MP4 using FFmpeg. It is categorised as a Execute tool in the Cutpilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cutpilot MCP server in PolicyLayer and add a rule for render_edit_plan: 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 Cutpilot. Nothing to install.
render_edit_plan is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the render_edit_plan 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 render_edit_plan. 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.
render_edit_plan is provided by the Cutpilot MCP server (Hellotravisss/cutpilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cutpilot, and thousands of servers like it.
Across the catalogue