Saved filter operations: list, get, get_tasks, list_parameters, save, rename, delete.\n\nActions:\n- list: List saved filters\n- get: Get one filter with parsed params (requires name)\n- get_tasks: Execute a filter against tasks (requires name)\n- list_parameters: List supported filter parameter ...
AI agents call noteplan_filters to permanently remove resources in Noteplan — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool spans multiple categories. The 'delete' action irreversibly removes saved filters, making this Destructive. The 'save' and 'rename' actions are Write-level, and 'get_tasks' executes a filter against tasks (Execute-level). Per the severity hierarchy, Destructive is the highest applicable category.
From the tool's definition Actions include 'delete: Delete a filter (requires name + dryRun/confirmationToken)' and 'save: Create or update a filter' and 'rename: Rename a filter'
Attacks that exploit this kind of access
Saved filter operations: list, get, get_tasks, list_parameters, save, rename, delete.\n\nActions:\n- list: List saved filters\n- get: Get one filter with parsed params (requires name)\n- get_tasks: Execute a filter against tasks (requires name)\n- list_parameters: List supported filter parameter keys\n- save: Create or update a filter (requires name + items)\n- rename: Rename a filter (requires oldName + newName)\n- delete: Delete a filter (requires name + dryRun/confirmationToken). It is categorised as a Destructive tool in the Noteplan MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Noteplan MCP server in PolicyLayer and add a rule for noteplan_filters: 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 Noteplan. Nothing to install.
noteplan_filters 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 noteplan_filters 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 noteplan_filters. 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.
noteplan_filters is provided by the Noteplan MCP server (@noteplanco/noteplan-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 →