Execute JavaScript in the React Native app context via CDP Runtime.evaluate. Use for inspecting state, refs, timers, or any runtime value. Expression runs in the global scope of the Hermes JS engine.
AI agents invoke evaluate_js to trigger actions in Mcp Rn 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.
This tool permits arbitrary JavaScript execution within a running React Native app's runtime environment. While it is primarily a debugging tool and not inherently destructive, it can execute code with side effects (modify state, trigger functions, access or mutate storage, make network requests, etc.).
From the tool's definition Tool description explicitly states 'Execute JavaScript in the React Native app context' and 'Expression runs in the global scope of the Hermes JS engine.' The use of CDP Runtime.evaluate confirms arbitrary code execution capabilities.
Attacks that exploit this kind of access
Execute JavaScript in the React Native app context via CDP Runtime.evaluate. Use for inspecting state, refs, timers, or any runtime value. Expression runs in the global scope of the Hermes JS engine. It is categorised as a Execute tool in the Mcp Rn Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Rn Devtools MCP server in PolicyLayer and add a rule for evaluate_js: 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 Mcp Rn Devtools. Nothing to install.
evaluate_js 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 evaluate_js 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 evaluate_js. 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.
evaluate_js is provided by the Mcp Rn Devtools MCP server (pablonortiz/mcp-rn-devtools). 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 →