AI agents use create_book to create or update resources in Tilnote — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tilnote environment.
This tool creates a new book, which is a write operation that modifies the data store by adding a new entry. It is reversible (the book can be deleted) and has no destructive or financial implications. The blast radius is limited to the user's own note-taking space. Severity is low because creating a book is a benign operation with minimal risk of accidental harm.
From the tool's definition Tool name 'create_book' and description 'Create a new book on Tilnote' explicitly indicate creation of a new resource, which is a reversible write operation.
Attacks that exploit this kind of access
Create a new book on Tilnote. Returns the book ID and URL. It is categorised as a Write tool in the Tilnote MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tilnote MCP server in PolicyLayer and add a rule for create_book: 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 Tilnote. Nothing to install.
create_book 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_book 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_book. 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_book is provided by the Tilnote MCP server (wisdomcrane/tilnote-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 →