search_crossref
AI agents call search_crossref to retrieve information from Paper Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to search the Crossref scholarly metadata database. Searching is a read-only operation with no side effects—it retrieves information without modifying, deleting, or executing arbitrary code. Despite the empty description, the naming pattern and server context strongly indicate a search function. Low severity because misuse would only expose already-published scholarly metadata.
From the tool's definition Tool name 'search_crossref' and sibling tools like 'search_papers', 'search_semantic', 'search_iacr' all perform searching operations.
Attacks that exploit this kind of access
search_crossref. It is categorised as a Read tool in the Paper Search MCP Server, which means it retrieves data without modifying state.
Register the Paper Search MCP server in PolicyLayer and add a rule for search_crossref: 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 Paper Search. Nothing to install.
search_crossref 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 search_crossref 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 search_crossref. 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.
search_crossref is provided by the Paper Search MCP server (its-antony/paper-search). 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 →