Execute JavaScript in the browser console
AI agents invoke puppeteer_evaluate to trigger actions in Puppeteer 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 executes arbitrary JavaScript, which is a classic Execute category action. Severity is critical because JavaScript evaluation in a browser can read sensitive data, modify page content, perform actions on behalf of the user, exfiltrate credentials, trigger unwanted network requests, or pivot to other attacks.
From the tool's definition Execute JavaScript in the browser console — this tool runs arbitrary code in a browser context with access to the DOM, APIs, and any data on the page.
Documented attack patterns abuse exactly the kind of access puppeteer_evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Puppeteer MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for puppeteer_evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"puppeteer_evaluate": {
"limits": [
{
"counter": "puppeteer_evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}puppeteer_evaluate 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 JavaScript in the browser console. It is categorised as a Execute tool in the Puppeteer MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Puppeteer MCP Server MCP server in PolicyLayer and add a rule for puppeteer_evaluate: 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 Puppeteer MCP Server. Nothing to install.
puppeteer_evaluate 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 puppeteer_evaluate 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 puppeteer_evaluate. 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.
puppeteer_evaluate is provided by the Puppeteer MCP Server MCP server (merajmehrabi/puppeteer-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Puppeteer 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.
8 Puppeteer MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.