Read note content. Pass a note key for one note, or a parent item key for all child notes.
AI agents call get_note to retrieve information from Zotero Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that retrieves note data from a Zotero library. It has no side effects, does not modify any data, and cannot cause destructive or financial harm. The blast radius of misuse is minimal—an agent could read all notes in a library, which may expose sensitive information but poses no irreversible risk.
From the tool's definition Tool name is 'get_note' and description explicitly states 'Read note content.' The operation retrieves existing notes without modification, creation, or deletion.
Attacks that exploit this kind of access
Read note content. Pass a note key for one note, or a parent item key for all child notes. It is categorised as a Read tool in the Zotero Assistant MCP Server, which means it retrieves data without modifying state.
Register the Zotero Assistant MCP server in PolicyLayer and add a rule for get_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 Zotero Assistant. Nothing to install.
get_note is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_note is provided by the Zotero Assistant MCP server (upascal/zotero-assistant-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 →