ocr_pdf

THE RISK

Low Risk

Why ocr_pdf needs a policy

OCR is a retrieval and analysis operation that extracts text from image-based PDFs without modifying, deleting, or executing external code. It produces derived data (text) from input without reversible or irreversible state changes to the document itself. This is a classic Read category operation.

From the tool's definition Tool name 'ocr_pdf' and description 'Perform OCR on scanned PDFs' indicate optical character recognition—a text extraction and analysis operation with no side effects on the document or external systems.

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

POLICY

How to control ocr_pdf

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ocr_pdf": {}
  }
}

ocr_pdf is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register MCP PDF — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP PDF tools

Write optimize_pdf Optimize PDF file size and performance Write reorder_pdf_pages Reorder pages in a PDF document Write repair_pdf Attempt to repair corrupted or damaged PDF files Write rotate_pages Rotate specific pages by 90, 180, or 270 degrees Write split_pdf Split PDF into multiple files at specified pages Write split_pdf_by_bookmarks Split PDF into separate files using bookmarks as breakpoints Write split_pdf_by_pages Split PDF into separate files by page ranges Write add_date_field Add a date field with format validation to PDF

All 46 MCP PDF tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ocr_pdf

What does the ocr_pdf tool do? +

Perform OCR on scanned PDFs. It is categorised as a Read tool in the MCP PDF MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ocr_pdf? +

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

What risk level is ocr_pdf? +

ocr_pdf is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ocr_pdf? +

Yes. Add a rate_limit block to the ocr_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 ocr_pdf completely? +

Set action: deny in the PolicyLayer policy for ocr_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 ocr_pdf? +

ocr_pdf is provided by the MCP PDF MCP server (rsp2k/mcp-pdf). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP PDF tool call.

Start from MCP PDF, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →