Download a paper and create a resource for it
AI agents use download_paper to create or update resources in ArXiv MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ArXiv MCP Server environment.
This tool downloads a paper and creates a new resource (likely a file or database entry). It is a Write operation because it creates new data/resources on the local system. It is reversible in the sense that the created resource can be deleted. Severity is medium because an AI agent could fill up storage by downloading many papers, but there is no direct data destruction or financial impact.
From the tool's definition Download a paper and create a resource for it
Attacks that exploit this kind of access
Download a paper and create a resource for it. It is categorised as a Write tool in the ArXiv MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ArXiv MCP Server MCP server in PolicyLayer and add a rule for download_paper: 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 ArXiv MCP Server. Nothing to install.
download_paper is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the download_paper 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 download_paper. 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.
download_paper is provided by the ArXiv MCP Server MCP server (wr-web/apr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →