recommend_papers
AI agents call recommend_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.
Based on the server's primary function of searching and retrieving academic papers, and the naming pattern of sibling tools, 'recommend_papers' almost certainly performs a Read operation—retrieving recommended papers from the server's data sources. With no destructive, financial, or code-execution capabilities evident, and no ability to modify data, this is classified as Read.
From the tool's definition Tool name 'recommend_papers' in a paper-search server context suggests retrieving or querying paper recommendations. The description is empty, which reduces confidence.
Attacks that exploit this kind of access
recommend_papers. 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 recommend_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.
recommend_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 recommend_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 recommend_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.
recommend_papers 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 →