Remove an email account configuration.
AI agents call imap_remove_account to permanently remove resources in Email MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing an email account configuration is an irreversible operation that deletes stored account data and access settings. This action cannot be easily reversed and fits the Destructive category (irreversibly deletes or overwrites data). While not as severe as deleting actual email messages, it permanently removes system configuration and could disrupt email service access.
From the tool's definition Tool name 'imap_remove_account' combined with description 'Remove an email account configuration' indicates deletion of account settings.
Attacks that exploit this kind of access
Remove an email account configuration. It is categorised as a Destructive tool in the Email MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Email MCP Server MCP server in PolicyLayer and add a rule for imap_remove_account: 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 Email MCP Server. Nothing to install.
imap_remove_account 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 imap_remove_account 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 imap_remove_account. 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.
imap_remove_account is provided by the Email MCP Server MCP server (sventern/mcp_email). 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 →