Run remaining RC Method steps automatically from the current step through Step 8 (Production Hardening). Auto-approves checkpoints between steps with a note that they were auto-approved. IMPORTANT: Does NOT auto-approve the Post-RC ship decision - that always requires human review. Use when the u...
AI agents invoke rc_autopilot to trigger actions in RC Engine. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers a multi-step automated workflow that executes product development processes (research, architecture, build, validation, hardening). While it explicitly requires human review for final ship decision, it still auto-executes and auto-approves intermediate steps, making intermediate decisions and state changes without human intervention.
From the tool's definition Tool description states it will 'Run remaining RC Method steps automatically' and 'auto-approves checkpoints between steps'.
Attacks that exploit this kind of access
Run remaining RC Method steps automatically from the current step through Step 8 (Production Hardening). Auto-approves checkpoints between steps with a note that they were auto-approved. IMPORTANT: Does NOT auto-approve the Post-RC ship decision - that always requires human review. Use when the user wants to fast-track the build pipeline. If any step fails, stops and reports where it stopped. Prerequisites: at least rc_start or rc_import_prerc must have been called. Not recommended for first-time users - prefer step-by-step flow. It is categorised as a Execute tool in the RC Engine MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the RC Engine MCP server in PolicyLayer and add a rule for rc_autopilot: 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_autopilot is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the rc_autopilot 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_autopilot. 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_autopilot 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 →