AI agents call zotero_read_pdf to retrieve information from Zotero 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 PDF document content from a Zotero library without side effects. It is purely informational—reading pages from existing attachments. There is no capability to modify, delete, or execute operations on the data, making it a straightforward Read operation with minimal security risk.
From the tool's definition Tool name 'zotero_read_pdf' and description 'Read a PDF attachment' explicitly indicate retrieval of document content. Parameters allow selecting specific attachments and pages but only for reading purposes.
Attacks that exploit this kind of access
Read a PDF attachment from a Zotero item. attachment_index selects which PDF (1-indexed, default=1). page_number reads a single page (1-indexed); if omitted, all pages are read. It is categorised as a Read tool in the Zotero MCP Server, which means it retrieves data without modifying state.
Register the Zotero MCP server in PolicyLayer and add a rule for zotero_read_pdf: 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. Nothing to install.
zotero_read_pdf 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_read_pdf 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_read_pdf. 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_read_pdf is provided by the Zotero MCP server (masaki39/zotero-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 →