Phase 2 (Define). Generates a Product Requirements Document from user-provided feature descriptions, user stories, and requirements. Produces an 11-section PRD saved to rc-method/prds/. Returns PRD content + gate prompt. Present the PRD to the user for review. Prerequisites: Phase 1 gate approved...
AI agents use rc_define 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.
The tool creates and saves a PRD file to disk. This is a Write operation — it produces and persists a structured document. There are no destructive, financial, or execution side effects. Severity is low because the output is a planning document with no operational impact.
From the tool's definition Generates a Product Requirements Document...saved to rc-method/prds/
Attacks that exploit this kind of access
Phase 2 (Define). Generates a Product Requirements Document from user-provided feature descriptions, user stories, and requirements. Produces an 11-section PRD saved to rc-method/prds/. Returns PRD content + gate prompt. Present the PRD to the user for review. Prerequisites: Phase 1 gate approved. After gate approval: moves to Phase 3 (Architect). Consider running ux_score on the feature list and ux_generate for UX-heavy products. 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 rc_define: 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.
rc_define 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 rc_define 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 rc_define. 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.
rc_define 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 →