AI agents call paper_references to retrieve information from Semantic Scholar 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 reference data from papers—a query operation with no side effects or data modification capability. It fits the Read category: retrieves or queries data with no side effects. While the description is empty, the tool name and server purpose strongly indicate a read-only operation on academic paper references.
From the tool's definition Tool name 'paper_references' and server context (Semantic Scholar API providing 'comprehensive access to academic paper data') indicate this retrieves reference information from academic papers.
Documented attack patterns abuse exactly the kind of access paper_references gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Semantic Scholar MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for paper_references:
{
"version": "1",
"default": "deny",
"tools": {
"paper_references": {}
}
}paper_references 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.
paper_references. It is categorised as a Read tool in the Semantic Scholar MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Semantic Scholar MCP Server MCP server in PolicyLayer and add a rule for paper_references: 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 Semantic Scholar MCP Server. Nothing to install.
paper_references 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_references 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_references. 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_references is provided by the Semantic Scholar MCP Server MCP server (zongmin-yu/semantic-scholar-fastmcp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 Semantic Scholar MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 Semantic Scholar MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.