Delete a note (moves to trash)
AI agents call vault_delete to permanently remove resources in Connect MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes notes from the user's Obsidian vault. Although moved to trash rather than permanently deleted, this is a destructive operation that cannot be easily undone by an AI agent and represents loss of user data. It is more severe than Write (which is reversible) and thus classified as Destructive.
From the tool's definition Tool name is vault_delete with description 'Delete a note (moves to trash)'. The verb 'delete' and the action of removing notes from the vault indicate irreversible data destruction, even though it moves to trash rather than permanently purging.
Attacks that exploit this kind of access
Delete a note (moves to trash). It is categorised as a Destructive tool in the Connect MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Connect MCP server in PolicyLayer and add a rule for vault_delete: 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 Connect MCP. Nothing to install.
vault_delete 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 vault_delete 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 vault_delete. 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.
vault_delete is provided by the Connect MCP server (joch/obsidian-connect-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 →