AI agents call get_item_fulltext 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 the full-text content of stored items (PDFs/documents) without creating, modifying, deleting, or executing any operations. It has no side effects on the data—it only reads. The blast radius of misuse is minimal: an agent could read unintended document contents, a confidentiality concern, but cannot alter system state or cause financial/destructive harm.
From the tool's definition Tool name is 'get_item_fulltext' and description states it 'Get[s] the full-text content of an item'; verb is 'Get' which indicates retrieval without modification. Supports 'pagination' which is a read operation pattern.
Attacks that exploit this kind of access
Get the full-text content of an item (usually a PDF attachment). - Supports pagination for large documents using offset and limit - Use. 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 get_item_fulltext: 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.
get_item_fulltext 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_item_fulltext 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_item_fulltext. 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_item_fulltext is provided by the Zotero MCP server (xbghc/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 →