factory_run_scene
Run a whole scene without changing or adopting its definition. For an optimization comparison, run the current baseline and pending draft candidate with the SAME input, expectedVersion and comparisonId; use role=baseline with target=current, then role=candidate with target=draft and pass BOTH the...
This record as markdown: /tools/dutydeck/factory-run-scene.md
What factory_run_scene does on DutyDeck
AI agents invoke factory_run_scene to trigger actions in DutyDeck. 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 factory_run_scene is rated High
factory_run_scene triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs factory_run_scene safely
PolicyLayer is an MCP gateway: it sits between your AI agents and DutyDeck, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For factory_run_scene, this is the rule to start with:
factory_run_scene 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 DutyDeck, apply this rule, and every factory_run_scene call is checked against it from then on.
Questions about factory_run_scene
Run a whole scene without changing or adopting its definition. For an optimization comparison, run the current baseline and pending draft candidate with the SAME input, expectedVersion and comparisonId; use role=baseline with target=current, then role=candidate with target=draft and pass BOTH the exact expectedDraftCreatedAt and expectedDraftDefinition returned by factory_get_scene. Comparison runs do not add duplicate saved tasks. The host rejects a changed version/draft and rejects a candidate with changes outside llm/extract prompts (including review standards, model slots, workflow or contracts), so prompt improvement cannot be manufactured by relaxing evaluation criteria or changing models. It is categorised as a Execute tool in the DutyDeck MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DutyDeck MCP server in PolicyLayer and add a rule for factory_run_scene: 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 DutyDeck. Nothing to install.
factory_run_scene 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 factory_run_scene 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 factory_run_scene. 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.
factory_run_scene is provided by the DutyDeck MCP server (taokoplay/DutyDeck). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on DutyDeck, and thousands of servers like it.
Across the catalogue