Execute JavaScript code in the page context
AI agents invoke browser_evaluate to trigger actions in Concurrent Browser MCP. 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.
This tool allows execution of JavaScript in the active page, which can trigger external operations, modify page state, exfiltrate data, or interact with third-party services. While not inherently destructive (it doesn't irreversibly delete data by itself), the ability to execute arbitrary code gives an AI agent broad capability to cause harm depending on the JavaScript payload.
From the tool's definition Tool description states 'Execute JavaScript code in the page context' — directly permits arbitrary code execution within a browser environment.
Documented attack patterns abuse exactly the kind of access browser_evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Concurrent Browser MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"browser_evaluate": {
"limits": [
{
"counter": "browser_evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_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 code in the page context. It is categorised as a Execute tool in the Concurrent Browser MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Concurrent Browser MCP server in PolicyLayer and add a rule for browser_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 Concurrent Browser MCP. Nothing to install.
browser_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 browser_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 browser_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.
browser_evaluate is provided by the Concurrent Browser MCP server (sailaoda/concurrent-browser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Concurrent Browser MCP, 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.
20 Concurrent Browser MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.