launch_chrome_manually · MCP Browser Text Reader MCP

WHAT IT DOES

What launch_chrome_manually does on MCP Browser Text Reader

AI agents invoke launch_chrome_manually to trigger actions in MCP Browser Text Reader. 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 launch_chrome_manually needs a policy

Launching a browser is an Execute category action because it triggers an external operation (Chrome process) whose side effects depend on what the browser subsequently does. While primarily a browser control tool for reading web content, the ability to launch browsers can be misused for automated browsing attacks, credential harvesting, or phishing.

From the tool's definition Tool description states 'launch_chrome_manually' and '手动启动Chrome浏览器（可见窗口）' (manually launch Chrome browser with visible window).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_chrome_manually Rate-limited

launch_chrome_manually 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": {
    "launch_chrome_manually": {
      "limits": [
        {
          "counter": "launch_chrome_manually_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 MCP Browser Text Reader, so you can run agents against it safely.

FAQ

Questions about launch_chrome_manually

What does the launch_chrome_manually tool do? +

手动启动Chrome浏览器（可见窗口）. It is categorised as a Execute tool in the MCP Browser Text Reader MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on launch_chrome_manually? +

Register the MCP Browser Text Reader MCP server in PolicyLayer and add a rule for launch_chrome_manually: 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 Browser Text Reader. Nothing to install.

What risk level is launch_chrome_manually? +

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

Can I rate-limit launch_chrome_manually? +

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

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

launch_chrome_manually is provided by the MCP Browser Text Reader MCP server (tikous/mymcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.