AI agents call get_paper_citations to retrieve information from Semanticscholar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries bibliographic metadata to retrieve citations pointing to a paper. It performs a passive lookup operation that neither modifies, deletes, nor executes any code. The data returned is read-only academic citation information. No destructive, financial, or execution-based actions are possible.
From the tool's definition Tool retrieves citation data that references a specified paper ('获取引用指定论文的文献列表' translates to 'get list of literature that cites a specified paper'). The verb 'get' and the retrieval-only nature indicate a query operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_paper_citations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Semanticscholar, and nothing reaches the server without passing your rules. This is the rule we recommend for get_paper_citations:
{
"version": "1",
"default": "deny",
"tools": {
"get_paper_citations": {}
}
}get_paper_citations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
获取引用指定论文的文献列表（谁引用了这篇论文）. It is categorised as a Read tool in the Semanticscholar MCP Server, which means it retrieves data without modifying state.
Register the Semanticscholar MCP server in PolicyLayer and add a rule for get_paper_citations: 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 Semanticscholar. Nothing to install.
get_paper_citations 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_paper_citations 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_paper_citations. 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_paper_citations is provided by the Semanticscholar MCP server (xbghc/semanticscholar-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Semanticscholar, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Semanticscholar tools catalogued and risk-classified — across an index of 43,000+ MCP servers.