browser_click · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What browser_click does on Claude Flow

AI agents invoke browser_click 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_click needs a policy

Browser click actions execute real browser automation that can trigger arbitrary application logic: submitting forms, initiating logins, purchasing flows, or any UI-driven side effect. The description explicitly mentions login flows with cookie reuse, meaning an AI agent could authenticate and act on behalf of users in downstream systems.

From the tool's definition 'Click an element using ref (@e1) or CSS selector' — triggers real browser automation including 'login flows with cookie reuse', 'JS-heavy SPA scraping', and DOM interactions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_click Rate-limited

browser_click 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_click": {
      "limits": [
        {
          "counter": "browser_click_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_click

What does the browser_click tool do? +

Click 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_click? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for browser_click: 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_click? +

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

Can I rate-limit browser_click? +

Yes. Add a rate_limit block to the browser_click 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_click completely? +

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

browser_click 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.