AI agents call list_screens to retrieve information from Mockit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a query/read operation on stored screen mockups. It retrieves information without side effects, making it categorically a Read operation. Severity is low as listing screens poses minimal risk—the worst case is information disclosure of already-generated UI mockups, which is low-impact. High confidence due to clear read-only semantics.
From the tool's definition Tool lists previously generated screens, filtered optionally by project name. No modification, deletion, or execution involved. Pure data retrieval operation.
Attacks that exploit this kind of access
List all generated screens, optionally filtered by project name. It is categorised as a Read tool in the Mockit MCP Server, which means it retrieves data without modifying state.
Register the Mockit MCP server in PolicyLayer and add a rule for list_screens: 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 Mockit. Nothing to install.
list_screens 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 list_screens 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 list_screens. 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.
list_screens is provided by the Mockit MCP server (karyaboyraz/mockit-mcp). 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 →