Add, remove, or replace tags on Zotero items. Works on any item type. Response includes before/after tag lists for verification. Confirm with user before executing.
AI agents use write_tag 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.
Tags are metadata that can be easily added, removed, or replaced without irreversible data loss. Changes are fully reversible through the same tool. This falls clearly into Write category (creates/modifies data reversibly) rather than Destructive, as tags are not core item data and modifications don't cause data loss.
From the tool's definition Tool description states 'Add, remove, or replace tags on Zotero items' — these are reversible metadata modifications typical of Write operations.
Documented attack patterns abuse exactly the kind of access write_tag 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_tag:
{
"version": "1",
"default": "deny",
"tools": {
"write_tag": {
"limits": [
{
"counter": "write_tag_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}write_tag 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.
Add, remove, or replace tags on Zotero items. Works on any item type. Response includes before/after tag lists for verification. 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_tag: 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_tag 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_tag 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_tag. 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_tag 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.