AI agents call get_screen_test_ids 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 is a read-only diagnostic tool for a React Native debugger. It queries and returns metadata about test identifiers on the screen, which is purely informational. There are no side effects, no data modifications, no code execution, and no financial implications. It is appropriate for initiating UI interaction flows by gathering information before further actions are taken.
From the tool's definition Tool name and description indicate it 'List testIDs present on the current screen with metadata' — a query operation that retrieves UI debugging information without modifying state or executing actions.
Attacks that exploit this kind of access
List testIDs present on the current screen with metadata. Start UI interaction flows with this tool before get_elements_by_test_id. 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_test_ids: 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_test_ids 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_test_ids 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_test_ids. 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_test_ids 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 →