Execute JavaScript in the browser and capture results plus DOM changes. Args: script: JavaScript code to execute (or JSON command for CDP operations). switch_tab_id: Switch to this tab before executing. no_monitor: Skip DOM change monitoring (faster, less info).
AI agents invoke browser_execute_js to trigger actions in Cdp Bridge. 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.
Executing arbitrary JavaScript in a browser session has high blast radius: can steal credentials, session tokens, modify page content, exfiltrate data, perform unauthorized actions on behalf of the user, or pivot to backend systems. While the tool itself is not destructive (data is not permanently deleted) or financial, execution of untrusted code is classified as Execute per the severity hierarchy.
From the tool's definition Tool description explicitly states "Execute JavaScript in the browser" and accepts "JavaScript code to execute" as script argument. This enables arbitrary code execution in the browser context.
Documented attack patterns abuse exactly the kind of access browser_execute_js gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cdp Bridge, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_execute_js:
{
"version": "1",
"default": "deny",
"tools": {
"browser_execute_js": {
"limits": [
{
"counter": "browser_execute_js_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_execute_js 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 and capture results plus DOM changes. Args: script: JavaScript code to execute (or JSON command for CDP operations). switch_tab_id: Switch to this tab before executing. no_monitor: Skip DOM change monitoring (faster, less info). It is categorised as a Execute tool in the Cdp Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cdp Bridge MCP server in PolicyLayer and add a rule for browser_execute_js: 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 Cdp Bridge. Nothing to install.
browser_execute_js 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_execute_js 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_execute_js. 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_execute_js is provided by the Cdp Bridge MCP server (unagi-cq/cdp-bridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Cdp Bridge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Cdp Bridge tools catalogued and risk-classified — across an index of 42,500+ MCP servers.