Access the cached full-text content database (read-only). Faster than re-extracting from Zotero. Actions: list (cached items), search (find text), get (retrieve content), stats (database info).
AI agents call fulltext_database to retrieve information from Zotero Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool provides query and retrieval capabilities only—listing cached items, searching for text, retrieving content, and retrieving statistics. No modifications, deletions, or side effects are possible. This is a straightforward read operation on an indexed database cache.
From the tool's definition Tool description explicitly states 'read-only' and lists actions limited to retrieval operations: 'list (cached items), search (find text), get (retrieve content), stats (database info)'.
Attacks that exploit this kind of access
Access the cached full-text content database (read-only). Faster than re-extracting from Zotero. Actions: list (cached items), search (find text), get (retrieve content), stats (database info). It is categorised as a Read tool in the Zotero Agent MCP Server, which means it retrieves data without modifying state.
Register the Zotero Agent MCP server in PolicyLayer and add a rule for fulltext_database: 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 Agent. Nothing to install.
fulltext_database 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 fulltext_database 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 fulltext_database. 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.
fulltext_database is provided by the Zotero Agent MCP server (psiQAQ/zotero-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
fulltext_database is one line of Zotero Agent's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →