Execute Playwright/TypeScript automation code against a Kernel browser session. If session_id is provided, uses that existing browser; otherwise creates a new one. Returns the result with a video replay URL. Auto-cleans up browsers it creates. Use computer_action with action
AI agents invoke execute_playwright_code to trigger actions in Kernel MCP Server. 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.
The tool runs user-supplied automation code in a browser context, which constitutes code execution. While not destructive by default, the blast radius is high because arbitrary TypeScript/Playwright code can perform any browser action (exfiltrate data, interact with web services, automate fraud, etc.). The mention of 'session_id' and browser management shows it controls real browser instances.
From the tool's definition Tool executes arbitrary 'Playwright/TypeScript automation code' against a browser session, enabling code execution whose effects depend on the code arguments provided.
Documented attack patterns abuse exactly the kind of access execute_playwright_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kernel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_playwright_code:
{
"version": "1",
"default": "deny",
"tools": {
"execute_playwright_code": {
"limits": [
{
"counter": "execute_playwright_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_playwright_code 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.
Free to start. No card required.
Execute Playwright/TypeScript automation code against a Kernel browser session. If session_id is provided, uses that existing browser; otherwise creates a new one. Returns the result with a video replay URL. Auto-cleans up browsers it creates. Use computer_action with action. It is categorised as a Execute tool in the Kernel MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kernel MCP Server MCP server in PolicyLayer and add a rule for execute_playwright_code: 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 Kernel MCP Server. Nothing to install.
execute_playwright_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_playwright_code 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.
Set action: deny in the PolicyLayer policy for execute_playwright_code. 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.
execute_playwright_code is provided by the Kernel MCP Server MCP server (kernel/kernel-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kernel MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 Kernel MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.