Get detailed information (abstract/metadata) for a specific ArXiv paper.
AI agents call read_paper to retrieve information from UniArticles 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 and presents existing academic paper information (abstract and metadata) from ArXiv. There is no data creation, modification, deletion, code execution, or financial transaction. The operation is read-only and cannot cause harm through misuse beyond accessing publicly available academic literature.
From the tool's definition Tool name 'read_paper' and description 'Get detailed information (abstract/metadata)' indicate retrieval of paper metadata without modification. The function retrieves abstract and metadata from ArXiv, which is a query operation with no side effects.
Documented attack patterns abuse exactly the kind of access read_paper gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and UniArticles MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_paper:
{
"version": "1",
"default": "deny",
"tools": {
"read_paper": {}
}
}read_paper 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.
Get detailed information (abstract/metadata) for a specific ArXiv paper. It is categorised as a Read tool in the UniArticles MCP Server MCP Server, which means it retrieves data without modifying state.
Register the UniArticles MCP Server MCP server in PolicyLayer and add a rule for read_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 UniArticles MCP Server. Nothing to install.
read_paper 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 read_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 read_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.
read_paper is provided by the UniArticles MCP Server MCP server (thinktraveller/uniarticles_mcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from UniArticles 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.
15 UniArticles MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.