AI agents use create_note to create or update resources in Zk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zk environment.
This tool performs a reversible create operation on notes within a local knowledge base. It does not execute code, delete data, move money, or cause irreversible changes. The impact is limited to note creation in a user's personal zk system, making it a Write category risk with low severity since notes can be edited or deleted afterward.
From the tool's definition The tool creates a new note with a specified title. The description explicitly states 'Create a new note', which is a reversible write operation that adds data to the knowledge base.
Attacks that exploit this kind of access
Create a new note with the specified title. It is categorised as a Write tool in the Zk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zk 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 Zk. 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 Zk MCP server (koei-kaji/zk-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 →