Search for notes across your Zotero library.
AI agents call zotero_search_notes to retrieve information from Zotero MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries note data without creating, modifying, deleting, or executing operations. It is a passive search function that returns matching results from the user's reference library. The blast radius of misuse is minimal—an AI agent could only read notes they have access to, with no ability to alter or destroy data.
From the tool's definition Tool name and description indicate searching/querying notes: 'Search for notes across your Zotero library.' The verb 'search' and lack of any modification language confirm read-only retrieval.
Attacks that exploit this kind of access
Search for notes across your Zotero library. It is categorised as a Read tool in the Zotero MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zotero MCP Server MCP server in PolicyLayer and add a rule for zotero_search_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 Zotero MCP Server. Nothing to install.
zotero_search_notes 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 zotero_search_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 zotero_search_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.
zotero_search_notes is provided by the Zotero MCP Server MCP server (tspspi/zotero-mcp-postgres-ollama-fulltext). 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 →