This record as markdown: /tools/45645678a-scholar-mcp/paper-recommend.md
What paper_recommend does on Scholar MCP Server
AI agents call paper_recommend to retrieve information from Scholar MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why paper_recommend is rated Low
paper_recommend performs local code analysis to suggest papers from the academic sources already available on the server. It retrieves and ranks existing data (papers) based on input parameters but does not create, modify, delete, or execute external actions. The operation is informational and reversible with no side effects.
From the tool's definition Tool analyzes workspace code and recommends relevant academic papers. The description indicates a retrieval/recommendation operation with no data modification, deletion, or external execution.
Attacks that exploit this kind of access
The rule that runs paper_recommend safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Scholar MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For paper_recommend, this is the rule to start with:
paper_recommend is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Scholar MCP Server, apply this rule, and every paper_recommend call is checked against it from then on.
Questions about paper_recommend
分析工作区代码，自动推荐相关学术论文。. It is categorised as a Read tool in the Scholar MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Scholar MCP Server MCP server in PolicyLayer and add a rule for paper_recommend: 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 Scholar MCP Server. Nothing to install.
paper_recommend 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 paper_recommend 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 paper_recommend. 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.
paper_recommend is provided by the Scholar MCP Server MCP server (45645678a/scholar-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Scholar MCP Server, and thousands of servers like it.
This server
Across the catalogue