AI agents call get_visible_elements 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 tool that queries and retrieves UI state information. It has no capacity to modify, delete, execute code, or trigger external operations. The 'fallback discovery' language reinforces it is informational only. Appropriate for debugging React Native applications where inspecting the UI structure is necessary without side effects.
From the tool's definition Tool returns/retrieves accessibility elements from current UI tree with no modification capability. Description explicitly states it returns flattened visible elements for discovery purposes only.
Attacks that exploit this kind of access
Return flattened visible accessibility elements derived from the current UI tree. Use as fallback discovery after testID-first lookup. 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_visible_elements: 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_visible_elements 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_visible_elements 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_visible_elements. 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_visible_elements 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 →