Call AFTER prc_start. Classifies the product idea using Cynefin framework (Clear/Complicated/Complex/Chaotic) and activates the appropriate subset of 20 research specialists. Returns: complexity domain, activated specialist list, estimated cost budget, and which stages to run. After success: pres...
AI agents call prc_classify to permanently remove resources in RC Engine — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call prc_classify doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from RC Engine is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Call AFTER prc_start. Classifies the product idea using Cynefin framework (Clear/Complicated/Complex/Chaotic) and activates the appropriate subset of 20 research specialists. Returns: complexity domain, activated specialist list, estimated cost budget, and which stages to run. After success: present the classification to the user as Checkpoint 1 - call prc_gate with their decision. Read-only analysis, no side effects beyond state update. It is categorised as a Destructive tool in the RC Engine MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RC Engine MCP server in PolicyLayer and add a rule for prc_classify: 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.
prc_classify is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the prc_classify 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 prc_classify. 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.
prc_classify 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 →