AI agents invoke execute_script to trigger actions in Chrome Tools 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.
This tool executes JavaScript in a Chrome tab, which can perform any action a script can do: modify the DOM, exfiltrate data, click buttons, navigate pages, or trigger external requests. The effects are entirely dependent on the arguments (the script content) and cannot be safely sandboxed. This is a core Execute risk.
From the tool's definition Tool name 'execute_script' combined with server description stating it 'execute[s] JavaScript' and enables 'remote control of Chrome tabs'.
Documented attack patterns abuse exactly the kind of access execute_script gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chrome Tools MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_script:
{
"version": "1",
"default": "deny",
"tools": {
"execute_script": {
"limits": [
{
"counter": "execute_script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_script 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_script. It is categorised as a Execute tool in the Chrome Tools MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Tools MCP Server MCP server in PolicyLayer and add a rule for execute_script: 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 Chrome Tools MCP Server. Nothing to install.
execute_script 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_script 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_script. 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_script is provided by the Chrome Tools MCP Server MCP server (nicholmikey/chrome-tools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Chrome Tools MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Chrome Tools MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.