browser_run_code_unsafe

A execute tool on the Playwright MCP server.

SERVERPlaywright SOURCEhanato238/playwright-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/hanato238-playwright-mcp/browser-run-code-unsafe.md

WHAT IT DOES

What browser_run_code_unsafe does on Playwright

AI agents invoke browser_run_code_unsafe to trigger actions in Playwright. 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.

RISK

Why browser_run_code_unsafe is rated High

The 'run_code_unsafe' designation strongly implies execution of arbitrary code within the browser environment. Combined with the server's automation capabilities and explicit 'unsafe' qualifier, this tool carries critical risk—an AI agent could execute malicious JavaScript, exfiltrate sensitive data from web pages, perform unauthorized actions on behalf of the user, or compromise browser security.

From the tool's definition Tool name contains 'run_code' and 'unsafe' suffix. Server enables 'browser automation' and tool naming pattern indicates arbitrary code execution in browser context without safety constraints.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_run_code_unsafe safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Playwright, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_run_code_unsafe, this is the rule to start with:

browser_run_code_unsafe Rate-limited

browser_run_code_unsafe 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_run_code_unsafe": {
      "limits": [
        {
          "counter": "browser_run_code_unsafe_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Playwright, apply this rule, and every browser_run_code_unsafe call is checked against it from then on.

FAQ

Questions about browser_run_code_unsafe

What does the browser_run_code_unsafe tool do? +

browser_run_code_unsafe is a execute tool on the Playwright MCP server. It is categorised as a Execute tool in the Playwright 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_run_code_unsafe? +

Register the Playwright MCP server in PolicyLayer and add a rule for browser_run_code_unsafe: 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 Playwright. Nothing to install.

What risk level is browser_run_code_unsafe? +

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

Can I rate-limit browser_run_code_unsafe? +

Yes. Add a rate_limit block to the browser_run_code_unsafe 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_run_code_unsafe completely? +

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

browser_run_code_unsafe is provided by the Playwright MCP server (hanato238/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Playwright, and thousands of servers like it.

This server

All 66 Playwright tools → High-risk tools on this server →

Across the catalogue

browser_click on Percepta MCP Server →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →