AI agents use rc_architect 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 rc_architect tool creates or modifies technical architecture specifications (tech stack, data models, API design, integrations, infrastructure). These are persistent design decisions that affect downstream build and deployment. While not executing code directly, the tool produces authoritative technical blueprints that developers will implement.
From the tool's definition Tool description states it 'Defines technical architecture: tech stack, data models, API design, integrations, and infrastructure.' The verb 'Defines' indicates creation or modification of design artifacts that shape system configuration.
Attacks that exploit this kind of access
Phase 3 (Architect). Defines technical architecture: tech stack, data models, API design, integrations, and infrastructure. Pass the user\. 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_architect: 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_architect 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_architect 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_architect. 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_architect 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 →