browser_launch

THE RISK

High Risk

Why browser_launch needs a policy

Launching a browser instance is an executable action that triggers external operations and can have unpredictable side effects depending on the arguments passed (URLs, extensions, flags, etc.).

From the tool's definition Tool description explicitly states it will 'Launch a new browser instance with debugging enabled' — this is a direct execution of a system operation that spawns a new process.

Documented attack patterns abuse exactly the kind of access browser_launch gives an agent:

POLICY

How to control browser_launch

PolicyLayer is an MCP gateway — it sits between your AI agents and Browser Connect, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_launch:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_launch": {
      "limits": [
        {
          "counter": "browser_launch_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_launch 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.

Create a free account and register Browser Connect — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Browser Connect tools

Execute performance_profile Advanced performance profiling with bottleneck detection and recommendations Execute debug_localhost Launch browser with a localhost URL and automatically connect for debugging Execute backend_debugger_attach Attach to a Node.js process debugger for breakpoint debugging Execute browser_connect Connect to a specific browser tab for debugging Read network_performance Get network performance statistics for a connected browser tab Read backend_logs_stream Stream and search logs from backend applications (files, processes, Docker containers) Read browser_list_tabs List all available browser tabs that can be connected to Read console_advanced_search Advanced console search with pattern matching, correlation, and statistics

All 16 Browser Connect tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Browser Connect → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about browser_launch

What does the browser_launch tool do? +

Launch a new browser instance with debugging enabled. It is categorised as a Execute tool in the Browser Connect 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_launch? +

Register the Browser Connect MCP server in PolicyLayer and add a rule for browser_launch: 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 Browser Connect. Nothing to install.

What risk level is browser_launch? +

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

Can I rate-limit browser_launch? +

Yes. Add a rate_limit block to the browser_launch 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_launch completely? +

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

browser_launch is provided by the Browser Connect MCP server (perception30/browser-connect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Browser Connect tool call.

Start from Browser Connect, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →