AI agents call confirm_doi to retrieve information from Zotero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries CrossRef to retrieve and validate DOI metadata before any add operation occurs. It performs only information retrieval (fetch, validate) without creating, modifying, deleting, or executing anything. No data is written to Zotero, no code is executed, and no irreversible changes occur. This is a safe, read-only operation.
From the tool's definition Tool description states 'Fetch metadata for a DOI from CrossRef to validate it exists' — a purely retrieval operation with no side effects on local data or external systems.
Attacks that exploit this kind of access
Fetch metadata for a DOI from CrossRef to validate it exists before adding to Zotero. It is categorised as a Read tool in the Zotero MCP Server, which means it retrieves data without modifying state.
Register the Zotero MCP server in PolicyLayer and add a rule for confirm_doi: 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.
confirm_doi 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 confirm_doi 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 confirm_doi. 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.
confirm_doi is provided by the Zotero MCP server (masaki39/zotero-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 →