Delete a frontmatter property from a note.
AI agents call obsidian_delete_property to permanently remove resources in Mcp Apple Obsidian — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes frontmatter properties from Obsidian notes. While individual property deletions have limited blast radius compared to note deletion, the action is inherently destructive and cannot be undone through normal means. It ranks as Destructive (not Write) because deletion is irreversible.
From the tool's definition Tool name 'obsidian_delete_property' and description 'Delete a frontmatter property from a note' explicitly state deletion of data from note metadata.
Attacks that exploit this kind of access
Delete a frontmatter property from a note. It is categorised as a Destructive tool in the Mcp Apple Obsidian MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Apple Obsidian MCP server in PolicyLayer and add a rule for obsidian_delete_property: 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 Apple Obsidian. Nothing to install.
obsidian_delete_property 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 obsidian_delete_property 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 obsidian_delete_property. 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.
obsidian_delete_property is provided by the Mcp Apple Obsidian MCP server (rex/mcp-apple-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 →