AI agents call rpc_get_screen_context to retrieve information from Rpcclient without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely queries the current state of the iOS screen and accessibility tree. It is a Read operation that provides context to other tools but does not itself create, modify, execute, delete, or move money.
From the tool's definition Tool returns 'current primary app context and visible accessibility elements' — it retrieves state information without modifying or executing actions. The verb 'Return' and 'get' in the function name indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Return current primary app context and visible accessibility elements. It is categorised as a Read tool in the Rpcclient MCP Server, which means it retrieves data without modifying state.
Register the Rpcclient MCP server in PolicyLayer and add a rule for rpc_get_screen_context: 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 Rpcclient. Nothing to install.
rpc_get_screen_context 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 rpc_get_screen_context 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 rpc_get_screen_context. 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.
rpc_get_screen_context is provided by the Rpcclient MCP server (appknox/rpcclient-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 →