AI agents call paper_search to retrieve information from Academic MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries academic paper metadata without modifying, executing, or deleting any data. It has no side effects beyond returning search results. The low severity reflects minimal blast radius—misuse would only result in unwanted paper results being retrieved, with no destructive or financial consequences.
From the tool's definition Tool name 'paper_search' combined with server description explicitly listing 'search' as one of its core functions: 'search, download, and read academic papers.' The tool is part of a read-only academic interface with sibling tools for downloading and…
Documented attack patterns abuse exactly the kind of access paper_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Academic MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for paper_search:
{
"version": "1",
"default": "deny",
"tools": {
"paper_search": {}
}
}paper_search 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_search. It is categorised as a Read tool in the Academic MCP MCP Server, which means it retrieves data without modifying state.
Register the Academic MCP server in PolicyLayer and add a rule for paper_search: 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 MCP. Nothing to install.
paper_search 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_search 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_search. 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_search is provided by the Academic MCP server (linxueyuanstdio/academic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Academic MCP, 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.
3 Academic MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.