Delete an OBS profile. Cannot remove the currently active profile.
AI agents call remove_profile to permanently remove resources in Obs — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes an OBS profile, which is a configuration container that cannot be restored through the tool's API. While it includes a safety guard (preventing deletion of the active profile), the action itself is irreversible and constitutes data destruction.
From the tool's definition 'Delete an OBS profile' - irreversible deletion of configuration data stored in OBS.
Attacks that exploit this kind of access
Delete an OBS profile. Cannot remove the currently active profile. It is categorised as a Destructive tool in the Obs MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Obs MCP server in PolicyLayer and add a rule for remove_profile: 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 Obs. Nothing to install.
remove_profile 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 remove_profile 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 remove_profile. 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.
remove_profile is provided by the Obs MCP server (larscangit/obs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
remove_profile is one line of Obs's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →