Remove a user from a group or project. dry_run=true by default. This is destructive.
AI agents call remove_member to permanently remove resources in Mcp Gitlab — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a member from a group or project is an irreversible action that cannot be easily undone—the user loses all access and permissions immediately. While marked as having dry_run=true by default (a safety measure), the actual execution permanently modifies access control, fitting the Destructive category.
From the tool's definition Tool description explicitly states 'Remove a user from a group or project' and 'This is destructive.' The action irreversibly revokes a user's access and membership.
Attacks that exploit this kind of access
Remove a user from a group or project. dry_run=true by default. This is destructive. It is categorised as a Destructive tool in the Mcp Gitlab MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Gitlab MCP server in PolicyLayer and add a rule for remove_member: 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 Mcp Gitlab. Nothing to install.
remove_member 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_member 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_member. 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_member is provided by the Mcp Gitlab MCP server (wanadev/gitlab-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 →