start_inspecting_native · React Devtools MCP: Risk & Policy

WHAT IT DOES

What start_inspecting_native does on React Devtools

AI agents invoke start_inspecting_native to trigger actions in React Devtools. 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.

WHY IT NEEDS A POLICY

Why start_inspecting_native needs a policy

This tool triggers an interactive inspection mode on a live React Native application, which constitutes execution of an operation whose effects depend on subsequent user/agent actions within that mode. While inspection itself is relatively safe (Read-like), the act of 'starting' an inspection mode that responds to taps/selections is an active operation that modifies the application's interactive state and behavior.

From the tool's definition The tool 'start_inspecting_native' activates an interactive inspection mode that triggers external operations (tap-to-select interactions) on a React Native application.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_inspecting_native Rate-limited

start_inspecting_native stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_inspecting_native": {
      "limits": [
        {
          "counter": "start_inspecting_native_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches React Devtools, so you can run agents against it safely.

FAQ

Questions about start_inspecting_native

What does the start_inspecting_native tool do? +

Start native element inspection mode (tap-to-select). It is categorised as a Execute tool in the React Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_inspecting_native? +

Register the React Devtools MCP server in PolicyLayer and add a rule for start_inspecting_native: 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 Devtools. Nothing to install.

What risk level is start_inspecting_native? +

start_inspecting_native is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_inspecting_native? +

Yes. Add a rate_limit block to the start_inspecting_native 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.

How do I block start_inspecting_native completely? +

Set action: deny in the PolicyLayer policy for start_inspecting_native. 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.

What MCP server provides start_inspecting_native? +

start_inspecting_native is provided by the React Devtools MCP server (skylarbarrera/react-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.