Delete a file from a repository. dry_run=true by default. This is destructive on the branch.
AI agents call delete_file 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.
File deletion from a repository is irreversible without access to git history recovery tools external to this MCP server. While the tool offers a dry_run safety default, the actual operation (when executed) causes permanent data loss on the specified branch.
From the tool's definition Tool description states 'Delete a file from a repository' and explicitly notes 'This is destructive on the branch.' The tool permanently removes file content from version control.
Attacks that exploit this kind of access
Delete a file from a repository. dry_run=true by default. This is destructive on the branch. 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_file: 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_file 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_file 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_file. 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_file 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 →