AI agents use notes to create or update resources in Tome — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tome environment.
Because the tool can delete notes (which is destructive) as well as write them, the most severe applicable category would normally be Destructive. However, notes are typically small, recoverable annotations rather than primary data, and the description suggests this is a lightweight annotation system. The blast radius of deleting a note is lower than deleting a paper or dataset.
From the tool's definition 'Read, write, or delete notes on papers or files' — the tool spans read, write, and delete operations
Attacks that exploit this kind of access
Read, write, or delete notes on papers or files. It is categorised as a Write tool in the Tome MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tome MCP server in PolicyLayer and add a rule for 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 Tome. Nothing to install.
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 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 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.
notes is provided by the Tome MCP server (retospect/tome-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 →