Inspect React state hooks by selector. Works with useState, Zustand, etc.
AI agents call inspect_state to retrieve information from React Native without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries the internal state of React components using selectors but does not create, modify, delete, or execute operations. It has no side effects and only provides visibility into application state. The lowest blast radius of misuse would be information disclosure rather than data corruption or execution of external operations.
From the tool's definition Tool name 'inspect_state' combined with description 'Inspect React state hooks by selector' indicates querying/retrieving state data without modification.
Attacks that exploit this kind of access
Inspect React state hooks by selector. Works with useState, Zustand, etc. It is categorised as a Read tool in the React Native MCP Server, which means it retrieves data without modifying state.
Register the React Native MCP server in PolicyLayer and add a rule for inspect_state: 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.
inspect_state 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 inspect_state 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 inspect_state. 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.
inspect_state 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 →