browser_press · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What browser_press does on Claude Flow

AI agents invoke browser_press 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_press needs a policy

This tool performs real browser automation actions (keypresses) within a live browser session. It can interact with login flows, submit forms, trigger JavaScript events, and manipulate authenticated sessions. As an Execute-category tool, misuse could exfiltrate data, manipulate web applications, or perform unintended actions within an authenticated browser context.

From the tool's definition "Press a keyboard key" and "real browser automation — JS-heavy SPA scraping, login flows with cookie reuse" — triggers actual browser interactions with external systems

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_press Rate-limited

browser_press 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_press": {
      "limits": [
        {
          "counter": "browser_press_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_press

What does the browser_press tool do? +

Press a keyboard key 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_press? +

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

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

Can I rate-limit browser_press? +

Yes. Add a rate_limit block to the browser_press 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_press completely? +

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

browser_press 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.