Permanently delete a project and all its data. This action is irreversible.
AI agents call delete_project to permanently remove resources in Redmine — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes an entire project and all associated data, which cannot be undone. This is the defining characteristic of a Destructive action. The blast radius is critical because a single misuse by an AI agent could eliminate significant work, issues, time entries, wiki pages, and all project metadata without recovery options. The description explicitly states the action is irreversible.
From the tool's definition "Permanently delete a project and all its data. This action is irreversible."
Attacks that exploit this kind of access
Permanently delete a project and all its data. This action is irreversible. It is categorised as a Destructive tool in the Redmine MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Redmine 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 Redmine. 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 Redmine MCP server (yenpu/redmine-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 →