Create a new Zotero item, re-parent existing attachments, or import a local file as an attachment. Common workflows: (1) read PDF → extract metadata → create item → attach PDF via attachmentKeys; (2) convert PDF to Markdown → import the .md file as attachment via import action. Confirm with user ...
AI agents use write_item to create or update resources in Zotero — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zotero environment.
The tool creates new items in Zotero (reversible Write operation) and imports/attaches files. While it modifies state, these actions are not destructive—items can be edited or deleted later. The severity is medium because misuse could pollute a research library with incorrect metadata or unwanted attachments, but the changes remain reversible.
From the tool's definition Tool description explicitly states: 'Create a new Zotero item' and 'import a local file as an attachment'. These are data creation and modification operations.
Documented attack patterns abuse exactly the kind of access write_item gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zotero, and nothing reaches the server without passing your rules. This is the rule we recommend for write_item:
{
"version": "1",
"default": "deny",
"tools": {
"write_item": {
"limits": [
{
"counter": "write_item_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}write_item stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new Zotero item, re-parent existing attachments, or import a local file as an attachment. Common workflows: (1) read PDF → extract metadata → create item → attach PDF via attachmentKeys; (2) convert PDF to Markdown → import the .md file as attachment via import action. Confirm with user before executing. It is categorised as a Write tool in the Zotero MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zotero MCP server in PolicyLayer and add a rule for write_item: 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.
write_item 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_item 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_item. 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_item is provided by the Zotero MCP server (zotero-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zotero, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
27 Zotero tools catalogued and risk-classified — across an index of 43,000+ MCP servers.