push_to_zotero
AI agents use push_to_zotero to create or update resources in BioCite-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BioCite-MCP environment.
This tool performs a write operation by pushing bibliographic data to Zotero, which creates or modifies reference entries. While reversible (entries can be deleted from Zotero), it commits data to an external system and could clutter or alter a user's bibliography if misused. Not destructive (data remains recoverable), not financial, and not execute-level (no arbitrary code execution).
From the tool's definition Tool name 'push_to_zotero' indicates writing/exporting data to an external reference management system (Zotero).
Attacks that exploit this kind of access
push_to_zotero. It is categorised as a Write tool in the BioCite-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the BioCite- MCP server in PolicyLayer and add a rule for push_to_zotero: 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 BioCite-MCP. Nothing to install.
push_to_zotero is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the push_to_zotero 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 push_to_zotero. 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.
push_to_zotero is provided by the BioCite- MCP server (muslus/biocite-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 →