Update metadata fields on Zotero items (title, abstract, date, URL, DOI, creators, etc.). Only works on regular items, not notes or attachments. Confirm with user before executing.
AI agents use write_metadata to create or update resources in Zotero Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zotero Agent environment.
This tool modifies existing bibliographic metadata in Zotero reversibly. Users can correct or change these fields again if needed, so it does not meet the Destructive threshold. It is not Execute (no code execution), Financial, or Read. The blast radius is medium because incorrect metadata updates could corrupt research records, but the operation is reversible and scoped to metadata fields only, not data deletion.
From the tool's definition Tool description states it 'Update[s] metadata fields on Zotero items (title, abstract, date, URL, DOI, creators, etc.)'. The verb 'update' and the list of modifiable fields (title, abstract, etc.) confirm this is a create/modify operation.
Attacks that exploit this kind of access
Update metadata fields on Zotero items (title, abstract, date, URL, DOI, creators, etc.). Only works on regular items, not notes or attachments. Confirm with user before executing. It is categorised as a Write tool in the Zotero Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zotero Agent MCP server in PolicyLayer and add a rule for write_metadata: 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.
write_metadata 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 write_metadata 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 write_metadata. 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.
write_metadata 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.
write_metadata 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 →