Retrieve items in the trash.
AI agents call trash_items to retrieve information from Mcp Zotero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists items that are already in a trash state—a read-only operation with no side effects. It does not delete, restore, or modify items; it only retrieves information about trashed items. The verb 'retrieve' confirms the Read category. Blast radius is minimal since viewing trash contents poses no risk of data loss or unintended changes.
From the tool's definition Tool name 'trash_items' with description 'Retrieve items in the trash' indicates a query/fetch operation that reads existing data without modification.
Attacks that exploit this kind of access
Retrieve items in the trash. It is categorised as a Read tool in the Mcp Zotero MCP Server, which means it retrieves data without modifying state.
Register the Mcp Zotero MCP server in PolicyLayer and add a rule for trash_items: 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 Mcp Zotero. Nothing to install.
trash_items 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 trash_items 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 trash_items. 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.
trash_items is provided by the Mcp Zotero MCP server (nealcaren/mcp-zotero). 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 →