playwright_run_cross_browser

THE RISK

High Risk

Why playwright_run_cross_browser needs a policy

This tool triggers the execution of test code against multiple browser instances simultaneously. While the intended use is QA testing, an AI agent could use natural language commands to run arbitrary browser automation scripts with side effects like submitting forms, clicking buttons, navigating to malicious sites, or scraping data. The parallel execution across multiple browsers amplifies the blast radius.

From the tool's definition Tool description states 'Run a test across multiple browsers...in parallel' which executes code (Playwright test scripts) against external systems.

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

POLICY

How to control playwright_run_cross_browser

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

policy.json

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

playwright_run_cross_browser 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 RunAutomation MCP Server — 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 RunAutomation MCP Server tools

Destructive clear_codegen_session Clear a code generation session without generating a test Destructive cleanup_idle_sessions Automatically close idle browser sessions that haven Destructive close_browser_session Close a specific browser session and cleanup all resources including browser instance, pag Destructive playwright_close Close the browser and release all resources Execute playwright_delete Perform an HTTP DELETE request Execute playwright_batch_ai_visual_compare Run batch AI visual comparisons across multiple pages Execute playwright_emulate_device Emulate a mobile device with specific viewport, user agent, and capabilities. Supports all Execute playwright_evaluate Execute JavaScript in the browser console

All 91 RunAutomation MCP Server 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 RunAutomation MCP Server → 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 playwright_run_cross_browser

What does the playwright_run_cross_browser tool do? +

Run a test across multiple browsers (chromium, firefox, webkit) in parallel. It is categorised as a Execute tool in the RunAutomation MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on playwright_run_cross_browser? +

Register the RunAutomation MCP Server MCP server in PolicyLayer and add a rule for playwright_run_cross_browser: 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 RunAutomation MCP Server. Nothing to install.

What risk level is playwright_run_cross_browser? +

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

Can I rate-limit playwright_run_cross_browser? +

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

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

playwright_run_cross_browser is provided by the RunAutomation MCP Server MCP server (tayyabakmal1/runautomation-mcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every RunAutomation MCP Server tool call.

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

CHECK YOUR STACK →