List available routes or navigate to a path in the app. Call without
AI agents invoke app_navigate to trigger actions in React Tools. 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.
Navigation in web applications triggers code execution, including route handlers, component mounting, API calls, and state changes. While not as severe as code injection, it can alter user experience, trigger unintended workflows, or expose sensitive pages. This is categorized as Execute rather than Write because navigation is an action that triggers operations whose side effects depend on the argument (the path).
From the tool's definition Tool description states 'navigate to a path in the app'. Navigation actions that change application state and trigger external operations (page loads, route handlers, side effects) constitute execution.
Documented attack patterns abuse exactly the kind of access app_navigate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and React Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for app_navigate:
{
"version": "1",
"default": "deny",
"tools": {
"app_navigate": {
"limits": [
{
"counter": "app_navigate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} app_navigate 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.
Free to start. No card required.
List available routes or navigate to a path in the app. Call without. It is categorised as a Execute tool in the React Tools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the React Tools MCP server in PolicyLayer and add a rule for app_navigate: 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 Tools. Nothing to install.
app_navigate 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 app_navigate 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 app_navigate. 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.
app_navigate is provided by the React Tools MCP server (mcp-fe/mcp-fe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from React Tools, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 React Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.