Remove a dependency between two tasks.
AI agents call remove_task_dependency to permanently remove resources in Todos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a dependency between tasks deletes that relationship. While it doesn't delete tasks themselves, removing a dependency link is typically not reversible without recreating it manually, and could cause task ordering or blocking logic to break unexpectedly. This classifies as Destructive with medium severity since the blast radius affects task coordination rather than data loss.
From the tool's definition 'Remove a dependency between two tasks' — removes an existing relationship/link between tasks, which is an irreversible deletion of that dependency record
Attacks that exploit this kind of access
Remove a dependency between two tasks. It is categorised as a Destructive tool in the Todos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todos MCP server in PolicyLayer and add a rule for remove_task_dependency: 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 Todos. Nothing to install.
remove_task_dependency 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 remove_task_dependency 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 remove_task_dependency. 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.
remove_task_dependency is provided by the Todos MCP server (@hasna/todos). 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 →