Open deep link on simulator/device. Navigate to screens via URL scheme.
AI agents invoke open_deeplink 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.
Opening a deep link triggers an external navigation operation on a device/simulator, executing a URL scheme that can launch app screens or external actions. This goes beyond a simple read — it actively drives app behavior. The blast radius is medium since a malicious deep link could navigate to sensitive screens or trigger in-app actions, but it is generally reversible.
From the tool's definition Open deep link on simulator/device. Navigate to screens via URL scheme.
Attacks that exploit this kind of access
Open deep link on simulator/device. Navigate to screens via URL scheme. 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 open_deeplink: 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.
open_deeplink 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 open_deeplink 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 open_deeplink. 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.
open_deeplink 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 →