Create, rename, move, or delete a folder in the Obsidian vault
AI agents call manage_folder to permanently remove resources in Obsidian MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly supports folder deletion, which is irreversible and can destroy entire subtrees of notes. Even rename/move operations could cause broken links or data loss at scale. The most severe applicable action (delete) drives the classification to Destructive with high severity given that deleting a folder in an Obsidian vault could wipe out large portions of a personal knowledge base irreversibly.
From the tool's definition 'Create, rename, move, or delete a folder in the Obsidian vault'
Attacks that exploit this kind of access
Create, rename, move, or delete a folder in the Obsidian vault. It is categorised as a Destructive tool in the Obsidian MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Obsidian MCP Server MCP server in PolicyLayer and add a rule for manage_folder: 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 Obsidian MCP Server. Nothing to install.
manage_folder 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 manage_folder 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 manage_folder. 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.
manage_folder is provided by the Obsidian MCP Server MCP server (markheramis/obsidian-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 →