Delete a GitLab project permanently.
AI agents call delete_project_tool 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.
Deleting a GitLab project is an irreversible operation that destroys all associated data including repositories, issues, merge requests, pipelines, and project configuration. This is the canonical example of a destructive action and represents the highest risk category. The blast radius is critical—a single misuse by an AI agent could destroy an entire project's history and work.
From the tool's definition Tool name 'delete_project_tool' combined with description 'Delete a GitLab project permanently.' The word 'permanently' indicates irreversible data loss.
Attacks that exploit this kind of access
Delete a GitLab project permanently. 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 delete_project_tool: 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.
delete_project_tool 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_project_tool 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_project_tool. 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_project_tool is provided by the MCP Gitlab MCP server (mcp-gitlab-crunchtools). 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 →