AI agents call get_bibliography 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 formats bibliographic information from existing Zotero items. It is a read-only operation that queries data without side effects, modifications, or deletions. The action is non-destructive and does not create, update, or remove any data. Misuse would have minimal impact since it only returns formatted citation data.
From the tool's definition Tool name 'get_bibliography' and description 'Get bibliography for multiple items' indicate retrieval of existing data with no modification or deletion of records.
Attacks that exploit this kind of access
Get bibliography for multiple items. 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_bibliography: 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_bibliography 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_bibliography 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_bibliography. 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_bibliography is provided by the Zotero MCP server (cr625/zotero-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_bibliography is one line of Zotero'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 →