AI agents call remove-todo to permanently remove resources in Todo MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes data from the database without possibility of recovery (assuming standard SQLite behavior without transaction rollback). This is a Destructive action. Severity is medium rather than high because the blast radius is limited to individual todo items in a personal database, not production systems or sensitive data at scale.
From the tool's definition Tool name 'remove-todo' indicates deletion of todo items. Server description states it supports 'remove operations'. Removing items from a persistent SQLite database is irreversible.
Documented attack patterns abuse exactly the kind of access remove-todo gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Todo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for remove-todo:
{
"version": "1",
"default": "deny",
"hide": [
"remove-todo"
]
}remove-todo disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
remove-todo. It is categorised as a Destructive tool in the Todo MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todo MCP Server 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 Todo MCP Server. 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 Todo MCP Server MCP server (leonvanzyl/todo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Todo MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Todo MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.