Delete your current profile photo.
AI agents call delete_profile_photo to permanently remove resources in Tgmcp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes user profile data (profile photo) which cannot be automatically restored. While the blast radius is limited compared to deleting entire accounts or messages, it is still irreversible destruction of user identity data. The 'delete' operation paired with profile data places it in the Destructive category rather than Write (which permits reversal).
From the tool's definition delete_profile_photo - irreversibly removes the user's profile photo without recovery mechanism
Attacks that exploit this kind of access
Delete your current profile photo. It is categorised as a Destructive tool in the Tgmcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tg MCP server in PolicyLayer and add a rule for delete_profile_photo: 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 Tgmcp. Nothing to install.
delete_profile_photo 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_profile_photo 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_profile_photo. 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_profile_photo is provided by the Tg MCP server (oevortex/tgmcp). 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 →