AI agents call rc_illuminate to retrieve information from RC Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
'Illuminate' as Phase 1 of a product development pipeline typically involves research, discovery, and information gathering rather than writing or executing operations. However, the description is cut off and provides minimal detail. Based on the pipeline context (structured research, architecture, build, validation) and the phase name suggesting insight/discovery, Read is the most likely category.
From the tool's definition Tool name 'rc_illuminate' and description 'Phase 1 (Illuminate). Call after rc_start, passing the user' — description is truncated and uninformative beyond indicating it is an early pipeline phase.
Attacks that exploit this kind of access
Phase 1 (Illuminate). Call after rc_start, passing the user. It is categorised as a Read tool in the RC Engine MCP Server, which means it retrieves data without modifying state.
Register the RC Engine MCP server in PolicyLayer and add a rule for rc_illuminate: 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_illuminate is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the rc_illuminate 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_illuminate. 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_illuminate 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 →