Delete/reject a friendship
AI agents call buddypress_delete_friendship to permanently remove resources in BuddyPress MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion of friendship data. While the damage is scoped to a single relationship, it cannot be undone without manual intervention and affects user relationships in the community. This meets the Destructive criteria as it removes data that cannot be easily recovered.
From the tool's definition Tool name explicitly contains 'delete' and description states 'Delete/reject a friendship' — this irreversibly removes a social relationship.
Attacks that exploit this kind of access
Delete/reject a friendship. It is categorised as a Destructive tool in the BuddyPress MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the BuddyPress MCP Server MCP server in PolicyLayer and add a rule for buddypress_delete_friendship: 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 BuddyPress MCP Server. Nothing to install.
buddypress_delete_friendship 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 buddypress_delete_friendship 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 buddypress_delete_friendship. 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.
buddypress_delete_friendship is provided by the BuddyPress MCP Server MCP server (vapvarun/buddypress-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 →