Start RC Method WITHOUT Pre-RC research. Use when user wants to go straight to building without the 20-persona research phase. Creates rc-method/ directory and project state, begins Phase 1 (Illuminate) with discovery questions. Returns discovery questions - present these to the user and collect ...
AI agents use rc_start 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 a directory and initializes project state, which is a reversible write operation. It does not execute code, delete data, or involve financial transactions. The blast radius is low as it only scaffolds a project structure.
From the tool's definition Creates rc-method/ directory and project state, begins Phase 1 (Illuminate) with discovery questions
Attacks that exploit this kind of access
Start RC Method WITHOUT Pre-RC research. Use when user wants to go straight to building without the 20-persona research phase. Creates rc-method/ directory and project state, begins Phase 1 (Illuminate) with discovery questions. Returns discovery questions - present these to the user and collect their answers. After success: call rc_illuminate with user answers. Do NOT use this if Pre-RC was run - use rc_import_prerc instead. 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_start: 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_start 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_start 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_start. 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_start 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.
rc_start is one line of RC Engine's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →