zk_create_note
AI agents use zk_create_note to create or update resources in Zettelkasten — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zettelkasten environment.
This tool creates new data entries (notes) in the Zettelkasten system. Creation of data is a Write operation—reversible and non-destructive. The severity is medium because a compromised agent could flood the system with spam notes or pollute the knowledge base, but the operation can be undone by using the sibling zk_delete_note tool.
From the tool's definition Tool name 'zk_create_note' indicates creation of new notes in the Zettelkasten system. The server description states it allows you to 'create, link, explore and synthesize atomic notes'. Tool creates reversible changes to the knowledge base.
Attacks that exploit this kind of access
zk_create_note. It is categorised as a Write tool in the Zettelkasten MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zettelkasten MCP server in PolicyLayer and add a rule for zk_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 Zettelkasten. Nothing to install.
zk_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 zk_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 zk_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.
zk_create_note is provided by the Zettelkasten MCP server (entanglr/zettelkasten-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 →