Remove a todo item from the current plan
AI agents call remove_todo to permanently remove resources in Software Planning Tool — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a todo item deletes it from the plan, which is typically irreversible without a separate undo mechanism. While the blast radius is limited to planning data (no financial or system-level impact), the action permanently eliminates a task entry, making it Destructive rather than merely Write.
From the tool's definition "Remove a todo item from the current plan" — the word 'remove' indicates deletion of a plan item.
Attacks that exploit this kind of access
Remove a todo item from the current plan. It is categorised as a Destructive tool in the Software Planning Tool MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Software Planning Tool MCP server in PolicyLayer and add a rule for remove_todo: 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 Software Planning Tool. Nothing to install.
remove_todo 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_todo 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_todo. 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_todo is provided by the Software Planning Tool MCP server (philippmt/software-planning-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 →