Run JS inside a WebView (DOM query, click, read text, etc). Use this instead of tap for any WebView content — tap cannot target DOM elements. Get webViewId via evaluate_script with getRegisteredWebViewIds().
AI agents invoke webview_evaluate_script to trigger actions in React Native. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary JavaScript code within a WebView context. While it can perform read operations (DOM query, read text), the primary capability and risk is executing code whose effects are determined by the injected script arguments. An AI agent could use this to exfiltrate data, manipulate the app's behavior, or trigger unintended actions within the WebView.
From the tool's definition Tool description explicitly states 'Run JS inside a WebView' with examples including DOM query, click, and read text operations. This is code execution in a potentially privileged context.
Attacks that exploit this kind of access
Run JS inside a WebView (DOM query, click, read text, etc). Use this instead of tap for any WebView content — tap cannot target DOM elements. Get webViewId via evaluate_script with getRegisteredWebViewIds(). It is categorised as a Execute tool in the React Native MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the React Native MCP server in PolicyLayer and add a rule for webview_evaluate_script: 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 React Native. Nothing to install.
webview_evaluate_script is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the webview_evaluate_script 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 webview_evaluate_script. 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.
webview_evaluate_script is provided by the React Native MCP server (@ohah/react-native-mcp-server). 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 →