AI agents use copy_iterate to create or update resources in RC Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RC Engine environment.
This tool modifies an existing document (COPY-SYSTEM.md) based on user feedback. This is a reversible write operation—the changes can be edited, reverted, or replaced. While it updates project documentation, the impact is scoped to a single file within a product development pipeline and does not delete data, execute arbitrary code, or trigger irreversible actions.
From the tool's definition Updates the COPY-SYSTEM.md in place
Attacks that exploit this kind of access
Iterate on the generated copy system with user feedback. Updates the COPY-SYSTEM.md in place. Optionally target specific screens for revision. It is categorised as a Write tool in the RC Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RC Engine MCP server in PolicyLayer and add a rule for copy_iterate: 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 RC Engine. Nothing to install.
copy_iterate 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 copy_iterate 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 copy_iterate. 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.
copy_iterate is provided by the RC Engine MCP server (originalrashmi/rc-engine-product-framework). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →