AI agents use create_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.
Creating a note modifies the Obsidian vault by adding new data (a file/document). This is a Write operation because it is reversible (the note can be deleted later). While the tool description is incomplete (cuts off mid-sentence at 'unless'), the intent to create data is clear.
From the tool's definition Tool name 'create_note' and verb 'Create a new note' indicate creation of data; the description explicitly states it 'Create[s] a new note', which is a reversible write operation.
Attacks that exploit this kind of access
Create a new note (fails if it already exists unless. 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 create_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.
create_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 create_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 create_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.
create_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.
create_note is one line of Obsidian's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →