read_by_ocr

A read tool on the MCP PDF MCP server.

SERVERMCP PDF Server SOURCEdeepseekmine/mcp-pdf-reader

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade A, identity unverified Pull the record →

This record as markdown: /tools/deepseekmine-mcp-pdf-reader/read-by-ocr.md

WHAT IT DOES

What read_by_ocr does on MCP PDF Server

AI agents call read_by_ocr to retrieve information from MCP PDF Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why read_by_ocr is rated Low

OCR is a text extraction technique that processes PDF content to make it machine-readable. This is a read operation with no side effects—it does not modify, delete, or execute external operations. The tool only retrieves data from PDF files. Severity is low because misuse would only expose PDF content, not cause destructive or financial harm.

From the tool's definition Tool name 'read_by_ocr' indicates optical character recognition (a read operation). Server description states the tool 'extracts text via normal parsing or OCR' and 'retrieves images from PDF files'.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs read_by_ocr safely

PolicyLayer is an MCP gateway: it sits between your AI agents and MCP PDF Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read_by_ocr, this is the rule to start with:

read_by_ocr Allowed

read_by_ocr is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect MCP PDF Server, apply this rule, and every read_by_ocr call is checked against it from then on.

FAQ

Questions about read_by_ocr

What does the read_by_ocr tool do? +

read_by_ocr is a read tool on the MCP PDF Server MCP server. It is categorised as a Read tool in the MCP PDF Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on read_by_ocr? +

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

What risk level is read_by_ocr? +

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

Can I rate-limit read_by_ocr? +

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

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

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

KEEP EXPLORING

More on MCP PDF Server, and thousands of servers like it.

This server

All 3 MCP PDF Server tools →

Across the catalogue

claude_read_file on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →