Medium Risk

batch_download_pdfs

批量并发下载多篇论文的 PDF 文件

How to control batch_download_pdfs ↓

What batch_download_pdfs does on Literature Review MCP Server

AI agents use batch_download_pdfs to create or update resources in Literature Review MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Literature Review MCP Server environment.

Medium Risk

Why batch_download_pdfs needs a policy

This tool downloads and writes PDF files to the local filesystem. Downloading creates new files on disk, which is a Write operation. It is not Destructive (no deletion), not Execute (no code execution), and not Financial. The blast radius is medium as it could consume disk space or download unwanted files if misused.

From the tool's definition 批量并发下载多篇论文的 PDF 文件 (Batch concurrent download of PDF files for multiple papers)

Risk signalsBulk/mass operation — affects multiple targets

Documented attack patterns abuse exactly the kind of access batch_download_pdfs gives an agent:

How to control batch_download_pdfs

PolicyLayer is an MCP gateway — it sits between your AI agents and Literature Review MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for batch_download_pdfs:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "batch_download_pdfs": {
      "limits": [
        {
          "counter": "batch_download_pdfs_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

batch_download_pdfs stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Literature Review MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about batch_download_pdfs

What does the batch_download_pdfs tool do? +

批量并发下载多篇论文的 PDF 文件. It is categorised as a Write tool in the Literature Review MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on batch_download_pdfs? +

Register the Literature Review MCP Server MCP server in PolicyLayer and add a rule for batch_download_pdfs: 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 Literature Review MCP Server. Nothing to install.

What risk level is batch_download_pdfs? +

batch_download_pdfs is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit batch_download_pdfs? +

Yes. Add a rate_limit block to the batch_download_pdfs 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.

How do I block batch_download_pdfs completely? +

Set action: deny in the PolicyLayer policy for batch_download_pdfs. 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.

What MCP server provides batch_download_pdfs? +

batch_download_pdfs is provided by the Literature Review MCP Server MCP server (ydzat/literature-review-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Literature Review MCP Server tool call.

Start from Literature Review 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.

16 Literature Review MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.