Generate a UX child PRD (PRD-[project]-ux.md). Call during Phase 2 (Define) if ux_score returned selective or deep_dive mode. Produces: screen inventory, state contracts, component inventory, copy inventory, and accessibility checklist. Saved alongside the main PRD in rc-method/prds/. Pass descri...
AI agents use ux_generate 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 creates new documentation files and structured data artifacts as part of a product development pipeline. It is reversible (files can be edited or deleted), has no destructive operations, does not execute external code or commands based on user input, and does not involve financial transactions. The primary action is creating/writing project documentation, making it a Write-category tool.
From the tool's definition Generates and produces a UX child PRD file (PRD-[project]-ux.md) that is 'Saved alongside the main PRD in rc-method/prds/'.
Attacks that exploit this kind of access
Generate a UX child PRD (PRD-[project]-ux.md). Call during Phase 2 (Define) if ux_score returned selective or deep_dive mode. Produces: screen inventory, state contracts, component inventory, copy inventory, and accessibility checklist. Saved alongside the main PRD in rc-method/prds/. Pass descriptions of the screens and user flows. After success: the UX PRD is used by rc_validate (Phase 5) for UX quality checks and by rc_forge_task for implementation guidance. 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 ux_generate: 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.
ux_generate 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 ux_generate 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 ux_generate. 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.
ux_generate 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 →