AI agents invoke launch_chrome to trigger actions in Chrome Debug 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.
Launching Chrome in debug mode is an Execute action because it initiates an external process with debugging capabilities that can be controlled programmatically. The blast radius is high since Chrome can then be used to visit arbitrary URLs, execute JavaScript, manage extensions, and perform user interactions.
From the tool's definition Tool launches Chrome in debug mode, enabling browser automation and control. Combined with sibling tools (evaluate, get_console_logs) and server description mentioning 'page automation, extension management, and userscript injection', this represents code…
Documented attack patterns abuse exactly the kind of access launch_chrome gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chrome Debug MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for launch_chrome:
{
"version": "1",
"default": "deny",
"tools": {
"launch_chrome": {
"limits": [
{
"counter": "launch_chrome_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}launch_chrome 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.
Launch Chrome in debug mode. It is categorised as a Execute tool in the Chrome Debug MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Debug MCP Server MCP server in PolicyLayer and add a rule for launch_chrome: 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 Debug MCP Server. Nothing to install.
launch_chrome 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 launch_chrome 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 launch_chrome. 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.
launch_chrome is provided by the Chrome Debug MCP Server MCP server (robertheadley/chrome-debug-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Chrome Debug MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Chrome Debug MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.