submit_export_job
Start a detached, persistent local export without blocking the Codex session. Supports video, audio, editable NLE interchange, and experimental Jianying drafts.
This record as markdown: /tools/cutpilot/submit-export-job.md
What submit_export_job does on Cutpilot
AI agents invoke submit_export_job 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 submit_export_job is rated High
This tool initiates a background export process that produces output files (video, audio, NLE interchange formats). It executes an operation with side effects (file creation on disk), but is not purely destructive or financial. The severity is medium because it consumes system resources and writes files, but misuse is largely recoverable by deleting outputs.
From the tool's definition "Start a detached, persistent local export" and "Supports video, audio, editable NLE interchange" — triggers an external export operation whose effects depend on arguments
Attacks that exploit this kind of access
The rule that runs submit_export_job 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 submit_export_job, this is the rule to start with:
submit_export_job 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 submit_export_job call is checked against it from then on.
Questions about submit_export_job
Start a detached, persistent local export without blocking the Codex session. Supports video, audio, editable NLE interchange, and experimental Jianying drafts. 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 submit_export_job: 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.
submit_export_job 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 submit_export_job 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 submit_export_job. 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.
submit_export_job 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