基于给定论文获取相关推荐论文
AI agents call get_recommended_papers to retrieve information from Academic Paper MCP HTTP/SSE Server 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 data—specifically recommendations derived from a given paper. It has no side effects, does not modify data, does not execute code, and does not delete or move resources. It is purely informational retrieval, consistent with the other read-only search and retrieval tools on this server.
From the tool's definition Tool name 'get_recommended_papers' and description indicate retrieval of paper recommendations based on input paper.
Attacks that exploit this kind of access
基于给定论文获取相关推荐论文. It is categorised as a Read tool in the Academic Paper MCP HTTP/SSE Server MCP Server, which means it retrieves data without modifying state.
Register the Academic Paper MCP HTTP/SSE Server MCP server in PolicyLayer and add a rule for get_recommended_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 Paper MCP HTTP/SSE Server. Nothing to install.
get_recommended_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 get_recommended_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 get_recommended_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.
get_recommended_papers is provided by the Academic Paper MCP HTTP/SSE Server MCP server (pastchais/academic-paper-mcp-http). 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 →