recommend_related_papers
AI agents call recommend_related_papers to retrieve information from Academic MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and recommends papers based on similarity or citation relationships—a pure read operation querying academic databases. It has no side effects, does not modify data, execute code, delete records, or involve financial transactions. The blast radius of misuse is minimal: an AI could retrieve irrelevant papers or recommendations, but this causes no permanent harm.
From the tool's definition Tool name 'recommend_related_papers' and server context indicate retrieval of paper recommendations without modification.
Attacks that exploit this kind of access
recommend_related_papers. It is categorised as a Read tool in the Academic MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Academic MCP Server MCP server in PolicyLayer and add a rule for recommend_related_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 Academic MCP Server. Nothing to install.
recommend_related_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_related_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_related_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_related_papers is provided by the Academic MCP Server MCP server (nanyang12138/academic-mcp-server). 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 →