Delete a note or folder from the vault.
AI agents call delete_note to permanently remove resources in Mcp Obsidian — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of notes or folders cannot be undone and permanently removes user data from the vault. This is a destructive operation with significant blast radius if triggered unintentionally by an AI agent (e.g., deleting important research notes, documentation, or entire folder structures). While the server implements path validation for security, the fundamental operation is irreversible data loss.
From the tool's definition Tool name is 'delete_note' and description explicitly states 'Delete a note or folder from the vault' — irreversible removal of data.
Attacks that exploit this kind of access
Delete a note or folder from the vault. It is categorised as a Destructive tool in the Mcp Obsidian MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Obsidian MCP server in PolicyLayer and add a rule for delete_note: 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 Mcp Obsidian. Nothing to install.
delete_note 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 delete_note 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 delete_note. 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.
delete_note is provided by the Mcp Obsidian MCP server (jkang8/mcp-obsidian). 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 →