Remove a user
AI agents call delete_user_permission to permanently remove resources in Bitbucket — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes a user's permissions or account relationship, which cannot be easily undone and has significant blast radius if invoked without proper authorization. This falls under Destructive (irreversible deletion) rather than Write (reversible modification). High severity due to the access control implications and permanence of the action.
From the tool's definition Tool name 'delete_user_permission' combined with description 'Remove a user' indicates permanent removal of user access/permissions. This is an irreversible operation affecting access control.
Attacks that exploit this kind of access
Remove a user. It is categorised as a Destructive tool in the Bitbucket MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Bitbucket MCP server in PolicyLayer and add a rule for delete_user_permission: 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 Bitbucket. Nothing to install.
delete_user_permission 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_user_permission 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_user_permission. 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_user_permission is provided by the Bitbucket MCP server (javimaligno/mcp-server-bitbucket). 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 →