Analyze the current UI state without performing any actions. Returns both a VLM-generated text description and the raw accessibility tree (view tree) of the current screen. Use to verify results after runcue_run, check what page is displayed, or inspect UI elements before deciding next steps. Par...
AI agents call runcue_check to retrieve information from RunCue without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs passive inspection and analysis of the current iOS app UI state. It retrieves information about screen layout and accessibility elements without causing side effects, modifications, or external operations. This is a classic Read operation (query/inspect pattern).
From the tool's definition Tool description states: 'Analyze the current UI state without performing any actions.' Returns 'VLM-generated text description and the raw accessibility tree' of the screen. Does not modify, delete, or execute operations—only queries and inspects UI state.
Attacks that exploit this kind of access
Analyze the current UI state without performing any actions. Returns both a VLM-generated text description and the raw accessibility tree (view tree) of the current screen. Use to verify results after runcue_run, check what page is displayed, or inspect UI elements before deciding next steps. Parameters: - deviceId: Required. Use the same simulator/device as the app under test. Do not pass. It is categorised as a Read tool in the RunCue MCP Server, which means it retrieves data without modifying state.
Register the RunCue MCP server in PolicyLayer and add a rule for runcue_check: 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 RunCue. Nothing to install.
runcue_check 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 runcue_check 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 runcue_check. 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.
runcue_check is provided by the RunCue MCP server (lihei12345/runcue). 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 →