Select a design option after reviewing ux_design output. Saves the selected option ID to project state so that design_iterate, design_challenge, and code generation know which option to use. REQUIRED for Deep Dive mode (UX score >= 7) before Gate 2 can be approved.
AI agents use design_select 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 or modifies project state by persisting a selection decision. It is a reversible write operation (the selection can be changed later) with no destructive or irreversible effects. There is no code execution, financial impact, or data deletion. The primary effect is updating internal state to track which design option is active in the pipeline.
From the tool's definition Saves the selected option ID to project state
Attacks that exploit this kind of access
Select a design option after reviewing ux_design output. Saves the selected option ID to project state so that design_iterate, design_challenge, and code generation know which option to use. REQUIRED for Deep Dive mode (UX score >= 7) before Gate 2 can be approved. 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 design_select: 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.
design_select 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 design_select 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 design_select. 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.
design_select 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 →