apply_natural_language_edit
Apply an explicitly reviewed natural-language edit plan as one validated project change. Destructive actions remain visible in the plan and approval is mandatory.
This record as markdown: /tools/cutpilot/apply-natural-language-edit.md
What apply_natural_language_edit does on Cutpilot
AI agents invoke apply_natural_language_edit 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 apply_natural_language_edit is rated High
The tool executes a natural-language edit plan against a video project, triggering real modifications. While it emphasizes review and approval, the tool itself performs the execution of changes — some of which are explicitly noted as destructive.
From the tool's definition 'Apply an explicitly reviewed natural-language edit plan as one validated project change' and 'Destructive actions remain visible in the plan and approval is mandatory'
Attacks that exploit this kind of access
The rule that runs apply_natural_language_edit 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 apply_natural_language_edit, this is the rule to start with:
apply_natural_language_edit 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 apply_natural_language_edit call is checked against it from then on.
Questions about apply_natural_language_edit
Apply an explicitly reviewed natural-language edit plan as one validated project change. Destructive actions remain visible in the plan and approval is mandatory. 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 apply_natural_language_edit: 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.
apply_natural_language_edit 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 apply_natural_language_edit 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 apply_natural_language_edit. 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.
apply_natural_language_edit 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