AI agents use move_note to create or update resources in Obsidian — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obsidian environment.
move_note is a reversible operation that modifies note locations and internal references. While it changes vault structure, it does not permanently delete data and can be undone. This places it in Write rather than Destructive. Severity is medium because careless mass-moving could disrupt vault organization, but the operation itself is recoverable.
From the tool's definition Tool explicitly performs 'move' and 'rename' operations on notes, which are reversible modifications. Description states it rewrites wiki-links, indicating structural changes to the vault.
Attacks that exploit this kind of access
Move a note from one path to another, optionally rewriting wiki-links so backlinks keep working. This is the safe way to rename notes — agents should not naively. It is categorised as a Write tool in the Obsidian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obsidian MCP server in PolicyLayer and add a rule for move_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 Obsidian. Nothing to install.
move_note is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the move_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 move_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.
move_note is provided by the Obsidian MCP server (yanxue06/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 →