This record as markdown: /tools/0xk3vin-vikunja-mcp/projects-delete.md
What projects_delete does on Vikunja
AI agents call projects_delete to permanently remove resources in Vikunja, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why projects_delete is rated Critical
Deleting a project is an irreversible operation that destroys data and cannot be undone. This is a destructive action affecting potentially significant collections of tasks, subtasks, and associated metadata. While not financial in nature, the high blast radius of accidentally deleting an entire project warrants 'high' severity—an AI agent with this capability could cause significant data loss if misdirected.
From the tool's definition Tool name 'projects_delete' and description 'Delete a project' directly indicate irreversible deletion of data.
Attacks that exploit this kind of access
The rule that runs projects_delete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Vikunja, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For projects_delete, this is the rule to start with:
projects_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Vikunja, apply this rule, and every projects_delete call is checked against it from then on.
Questions about projects_delete
Delete a project. It is categorised as a Destructive tool in the Vikunja MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vikunja MCP server in PolicyLayer and add a rule for projects_delete: 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 Vikunja. Nothing to install.
projects_delete 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 projects_delete 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 projects_delete. 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.
projects_delete is provided by the Vikunja MCP server (0xk3vin/vikunja-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vikunja, and thousands of servers like it.
Across the catalogue