factory_prepare_operation
Step 1 of 2 for scene lifecycle, draft adoption/discard, rollback, export, dataset changes, or stub deletion. 场景操作属于当前工作区；修改或增加步骤时沿用已有 sceneId，只有用户明确要求新建独立场景时才使用 createScene。Freezes the exact target state and returns an approval snapshot; writes nothing. For a single-block adoption, explicitly us...
This record as markdown: /tools/dutydeck/factory-prepare-operation.md
What factory_prepare_operation does on DutyDeck
AI agents use factory_prepare_operation to create or update resources in DutyDeck, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DutyDeck environment.
Why factory_prepare_operation is rated Medium
An AI agent can call factory_prepare_operation faster than any human can review: one bad instruction and it creates or modifies resources in DutyDeck by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs factory_prepare_operation 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_prepare_operation, this is the rule to start with:
factory_prepare_operation stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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_prepare_operation call is checked against it from then on.
Questions about factory_prepare_operation
Step 1 of 2 for scene lifecycle, draft adoption/discard, rollback, export, dataset changes, or stub deletion. 场景操作属于当前工作区；修改或增加步骤时沿用已有 sceneId，只有用户明确要求新建独立场景时才使用 createScene。Freezes the exact target state and returns an approval snapshot; writes nothing. For a single-block adoption, explicitly use adoptDraft scope kind=step or kind=stepAcceptance; omitting scope means the WHOLE draft. Unselected draft changes remain pending. Partial scope MUST NOT include testedBatchId because whole-draft evidence cannot prove a partial adoption. testedExperimentId may certify a partial adoption only when the host verifies the actual merged definition exactly matches the frozen tested candidate. First save the candidate prompt into the existing draft through its approval flow, preserving other pending blocks; experiments never overwrite drafts. Every new adoptDraft request MUST include proposal with a concrete problem and expected benefit; risk is optional. Proposal is an Agent judgment awaiting review, never a test conclusion. The host separately derives verified benefits, current problems, remaining risks, and validation scope only from matching test evidence. Legacy internal calls without proposal remain readable through the exact draft diff and note. It is categorised as a Write tool in the DutyDeck MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DutyDeck MCP server in PolicyLayer and add a rule for factory_prepare_operation: 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_prepare_operation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the factory_prepare_operation 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_prepare_operation. 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_prepare_operation 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.
This server
Across the catalogue