获取论文的引用和被引用信息
AI agents call get_citation_info 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 retrieves bibliometric metadata (citations and references) from academic databases. It queries existing data without creating, modifying, deleting, or executing any operations. No side effects or state changes occur. Blast radius if misused is minimal—an agent could retrieve citation data inefficiently or make many requests, but cannot harm systems or data integrity.
From the tool's definition Tool name 'get_citation_info' and description '获取论文的引用和被引用信息' (retrieve citation and cited-by information for papers) indicate data retrieval only.
Attacks that exploit this kind of access
获取论文的引用和被引用信息. 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_citation_info: 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_citation_info 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_citation_info 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_citation_info. 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_citation_info 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 →