AI agents call get_screen_context to retrieve information from Rn Debug without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves debugging information about the Android screen state to support troubleshooting and remediation guidance. It has no side effects, does not execute code or commands, does not modify data, and does not delete or move resources. The primary purpose is diagnostic data collection, which is characteristic of Read category tools.
From the tool's definition Tool description states 'Get inferred current Android screen context' — a retrieval operation that queries the current state of the debug interface without modifying or executing anything. The action is read-only information gathering.
Attacks that exploit this kind of access
Get inferred current Android screen context for remediation guidance. Use after testID lookup fails. It is categorised as a Read tool in the Rn Debug MCP Server, which means it retrieves data without modifying state.
Register the Rn Debug MCP server in PolicyLayer and add a rule for 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 Rn Debug. Nothing to install.
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 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 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.
get_screen_context is provided by the Rn Debug MCP server (rn-debug-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 →