AI agents use remnote_create_note to create or update resources in Remnote — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Remnote environment.
This tool creates new notes with optional content, parent references, and tags. It is reversible (notes can be deleted), modifies the knowledge base state, and represents a Write operation rather than Read (no data retrieval) or Destructive (not irreversible, as created notes can be deleted).
From the tool's definition Tool name is 'remnote_create_note' and description states 'Create a new note in RemNote' — explicitly creates new data in the knowledge base.
Attacks that exploit this kind of access
Create a new note in RemNote with optional content, parent, and exact tag Rem IDs. Supports hierarchical markdown in content and flashcard syntax (e.g. It is categorised as a Write tool in the Remnote MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Remnote MCP server in PolicyLayer and add a rule for remnote_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 Remnote. Nothing to install.
remnote_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 remnote_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 remnote_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.
remnote_create_note is provided by the Remnote MCP server (remnote-mcp-server). 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 →