AI agents call check_zotero_status to retrieve information from ZotLink without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query operation that determines whether Zotero is running and accessible. It has no side effects, does not modify any data, and only returns status information. The blast radius of misuse is minimal—an AI agent cannot cause harm by checking a service's availability repeatedly.
From the tool's definition Tool checks the status/reachability of Zotero without modifying, creating, deleting, or executing operations. It retrieves the state of an external service.
Documented attack patterns abuse exactly the kind of access check_zotero_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ZotLink, and nothing reaches the server without passing your rules. This is the rule we recommend for check_zotero_status:
{
"version": "1",
"default": "deny",
"tools": {
"check_zotero_status": {}
}
}check_zotero_status is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check if Zotero is running and reachable. It is categorised as a Read tool in the ZotLink MCP Server, which means it retrieves data without modifying state.
Register the ZotLink MCP server in PolicyLayer and add a rule for check_zotero_status: 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 ZotLink. Nothing to install.
check_zotero_status 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 check_zotero_status 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 check_zotero_status. 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.
check_zotero_status is provided by the ZotLink MCP server (tonybotni/zotlink). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 ZotLink tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 ZotLink tools catalogued and risk-classified — across an index of 42,500+ MCP servers.