Find noteworthy new research published in the last N days.
AI agents call discover_recent_papers 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 queries and retrieves academic paper metadata without modifying, executing, or destroying data. It is purely informational read access to published research records. Severity is low because misuse would only result in retrieving information that is already publicly available.
From the tool's definition Tool description states 'Find noteworthy new research published in the last N days' — a retrieval operation with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Find noteworthy new research published in the last N days. 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 discover_recent_papers: 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.
discover_recent_papers 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 discover_recent_papers 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 discover_recent_papers. 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.
discover_recent_papers is provided by the Paper Search MCP server (upascal/paper-search-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 →