Phase 5 (Validate). QUALITY GATE before building. Runs 4 automated checks: anti-pattern scan, token budget audit, scope drift detection, and UX quality assessment. This catches problems BEFORE code is written - saving significant rework. No user input needed. Present findings to user with severit...
AI agents invoke rc_validate 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.
The tool executes a series of automated analysis/validation routines against existing artifacts. It does not merely read static data but actively runs multiple diagnostic processes and produces derived findings with severity ratings. This qualifies as Execute rather than Read, since it triggers external operations (scans, audits, assessments) whose outputs depend on the current pipeline state.
From the tool's definition Runs 4 automated checks: anti-pattern scan, token budget audit, scope drift detection, and UX quality assessment
Attacks that exploit this kind of access
Phase 5 (Validate). QUALITY GATE before building. Runs 4 automated checks: anti-pattern scan, token budget audit, scope drift detection, and UX quality assessment. This catches problems BEFORE code is written - saving significant rework. No user input needed. Present findings to user with severity ratings. Prerequisites: Phase 4 gate approved. After gate approval: moves to Phase 6 (Forge) - begin building with rc_forge_task. 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_validate: 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_validate 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_validate 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_validate. 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_validate 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 →