AI agents use create_notes 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.
This tool creates new notes (data) in the vault, which is a Write operation. Severity is medium because while note creation is reversible (notes can be deleted), creating many notes at once could disrupt a user's vault structure, fill it with unwanted content, or interfere with existing organization.
From the tool's definition Tool description states 'Create many notes in a single tool call' and explicitly mentions 'bootstrapping a knowledge graph'. The verb 'Create' and the batch operation confirm this creates new data reversibly within the Obsidian vault.
Attacks that exploit this kind of access
Create many notes in a single tool call. Designed for bootstrapping a knowledge graph (MOC + topical notes) without paying N round-trips. Each entry follows the same schema as. 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_notes: 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_notes 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_notes 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_notes. 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_notes 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 →