Delete a GitLab project.
AI agents call delete_project to permanently remove resources in GitLab MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of a project cannot be undone and represents permanent loss of code repositories, issues, merge requests, CI/CD history, and all related artifacts. This is the highest-impact destructive action available in a GitLab context. The blast radius is critical if an AI agent misuses this tool against the wrong project or without proper authorization.
From the tool's definition Tool name 'delete_project' and description 'Delete a GitLab project' explicitly perform irreversible deletion of an entire project and all its associated data.
Attacks that exploit this kind of access
Delete a GitLab project. It is categorised as a Destructive tool in the GitLab MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitLab MCP Server MCP server in PolicyLayer and add a rule for delete_project: 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 GitLab MCP Server. Nothing to install.
delete_project 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 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. 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 is provided by the GitLab MCP Server MCP server (skmprb/gitlab-clone-mcp-server). 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 →