AI agents call search_semantic_scholar 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 searches academic papers in Semantic Scholar, a public academic database. Search operations are read-only queries that retrieve information without modifying, executing code, deleting data, or committing financial obligations. No destructive or state-changing actions are possible. Low severity reflects minimal blast radius—an AI agent cannot cause harm by searching papers.
From the tool's definition Tool name 'search_semantic_scholar' combined with server description stating it 'search papers' and 'retrieves...paper and author details' through a read-only academic API.
Documented attack patterns abuse exactly the kind of access search_semantic_scholar 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 search_semantic_scholar:
{
"version": "1",
"default": "deny",
"tools": {
"search_semantic_scholar": {}
}
}search_semantic_scholar 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.
search_semantic_scholar. 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 search_semantic_scholar: 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.
search_semantic_scholar 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 search_semantic_scholar 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 search_semantic_scholar. 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.
search_semantic_scholar is provided by the Semantic Scholar MCP Server MCP server (jackkuo666/semanticscholar-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Semantic Scholar MCP Server, 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.
4 Semantic Scholar MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.