Uninstalls a Chrome extension by its ID.
AI agents call uninstall_extension to permanently remove resources in Chrome Devtools — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Uninstalling a Chrome extension removes it from the browser permanently. This is an irreversible destructive action — the extension's configuration and state may be lost. An AI agent misusing this tool could remove critical browser extensions (security tools, password managers, etc.) without the user's consent.
From the tool's definition 'Uninstalls a Chrome extension by its ID' — uninstalling is an irreversible removal action
Attacks that exploit this kind of access
Uninstalls a Chrome extension by its ID. It is categorised as a Destructive tool in the Chrome Devtools MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for uninstall_extension: 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 Devtools. Nothing to install.
uninstall_extension is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the uninstall_extension 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 uninstall_extension. 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.
uninstall_extension is provided by the Chrome Devtools MCP server (nimbus21/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →