AI agents call delete_email to permanently remove resources in Freshdesk — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible action—deletion of email messages—which cannot be undone once executed. Even though 'move to trash' may offer a brief recovery window in some systems, the primary function is destructive data removal. This poses a high blast radius if an AI agent mistakenly deletes important customer support emails, business records, or sensitive correspondence in a Freshdesk support context.
From the tool's definition Tool name 'delete_email' and description 'Delete or move an email to trash' explicitly indicate permanent removal or irreversible relocation of email data.
Documented attack patterns abuse exactly the kind of access delete_email gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Freshdesk, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_email:
{
"version": "1",
"default": "deny",
"hide": [
"delete_email"
]
} delete_email disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete or move an email to trash. It is categorised as a Destructive tool in the Freshdesk MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Freshdesk MCP server in PolicyLayer and add a rule for delete_email: 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 Freshdesk. Nothing to install.
delete_email 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 delete_email 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 delete_email. 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.
delete_email is provided by the Freshdesk MCP server (@mindstone-engineering/mcp-server-freshdesk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Freshdesk, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
422 Freshdesk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.