AI agents call paper_read 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.
The tool reads academic papers from databases without modifying, deleting, or executing any code. It is a straightforward data retrieval operation with no side effects. Low severity because the worst-case misuse (reading papers a user shouldn't access) has minimal blast radius in an academic context.
From the tool's definition Tool named 'paper_read' with empty description, but context from sibling tools (paper_download, paper_search) and server purpose ('search, download, and read academic papers') clearly indicates retrieval of paper content.
Documented attack patterns abuse exactly the kind of access paper_read 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_read:
{
"version": "1",
"default": "deny",
"tools": {
"paper_read": {}
}
}paper_read 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_read. 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_read: 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_read 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_read 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_read. 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_read 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.