AI agents use rc_gate 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 appears to accept and process user submissions through a gate/approval mechanism, which constitutes a Write operation (creates records, advances workflow state). The severity is medium given the context of a product development pipeline where submissions affect project progression but do not destroy data or execute arbitrary code. Confidence is reduced due to the truncated and uninformative description.
From the tool's definition Tool name 'rc_gate' with description 'Submit user' suggests a submission/gating mechanism that creates or modifies records in a product development pipeline. The incomplete description limits confidence.
Attacks that exploit this kind of access
Submit 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_gate: 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_gate 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_gate 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_gate. 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_gate 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 →