OPTIONAL - call during Phase 2 (Define) to assess UX complexity. Pass the feature list from the PRD. Returns: numeric score, mode (standard/selective/deep_dive), and which UX specialist modules to load. Use the result to decide whether to call ux_generate (for deep_dive/selective) or skip UX chil...
AI agents call ux_score to retrieve information from RC Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes data to inform decision-making but produces no side effects, modifications, or triggered operations. It is purely analytical and advisory in nature, making it a Read category tool with low severity since misuse would only provide incorrect guidance without operational impact.
From the tool's definition The tool performs 'Read-only analysis' and returns assessment results (numeric score, mode, and module recommendations) without creating, modifying, or executing any operations.
Attacks that exploit this kind of access
OPTIONAL - call during Phase 2 (Define) to assess UX complexity. Pass the feature list from the PRD. Returns: numeric score, mode (standard/selective/deep_dive), and which UX specialist modules to load. Use the result to decide whether to call ux_generate (for deep_dive/selective) or skip UX child PRD (for standard). Does NOT require project_path - works on any feature list. Read-only analysis. It is categorised as a Read tool in the RC Engine MCP Server, which means it retrieves data without modifying state.
Register the RC Engine MCP server in PolicyLayer and add a rule for ux_score: 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_score is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ux_score 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_score. 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_score 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 →