Medium Risk

split_pdf

Split a PDF into multiple files by page ranges (e.g.

How to control split_pdf ↓

AI agents use split_pdf to create or update resources in PDF Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PDF Tools environment.

Medium Risk

Splitting a PDF creates new output files from an existing source. The original file is not necessarily destroyed (non-destructive), but new files are written to disk. This is a Write operation with medium severity since it produces multiple new files but does not irreversibly delete the source.

From the tool's definition Split a PDF into multiple files by page ranges

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

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

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

split_pdf 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 PDF Tools — 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.

Go deeper

What does the split_pdf tool do? +

Split a PDF into multiple files by page ranges (e.g. It is categorised as a Write tool in the PDF Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on split_pdf? +

Register the PDF Tools MCP server in PolicyLayer and add a rule for split_pdf: 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 PDF Tools. Nothing to install.

What risk level is split_pdf? +

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

Can I rate-limit split_pdf? +

Yes. Add a rate_limit block to the split_pdf 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 split_pdf completely? +

Set action: deny in the PolicyLayer policy for split_pdf. 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 split_pdf? +

split_pdf is provided by the PDF Tools MCP server (open-document-alliance/pdf-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PDF Tools tool call.

Deterministic rules across all 36 PDF Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

36 PDF Tools tools catalogued and risk-classified — across an index of 42,500+ 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.