browser_hover · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What browser_hover does on Claude Flow

AI agents invoke browser_hover to trigger actions in Claude Flow. 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 browser_hover needs a policy

This tool performs a browser action (hover) within a real browser automation context, triggering JavaScript event handlers and potentially altering application state. It falls under Execute because it runs browser interactions that can have side effects depending on the target element and page context (e.g., revealing hidden menus, triggering JS events).

From the tool's definition Hover over an element using ref (@e1) or CSS selector ... you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_hover Rate-limited

browser_hover 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": {
    "browser_hover": {
      "limits": [
        {
          "counter": "browser_hover_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about browser_hover

What does the browser_hover tool do? +

Hover over an element using ref (@e1) or CSS selector Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude. For static HTML pages, native WebFetch is faster and free. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_hover? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for browser_hover: 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 Claude Flow. Nothing to install.

What risk level is browser_hover? +

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

Can I rate-limit browser_hover? +

Yes. Add a rate_limit block to the browser_hover 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 browser_hover completely? +

Set action: deny in the PolicyLayer policy for browser_hover. 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 browser_hover? +

browser_hover is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.