get_help

THE RISK

Low Risk

Why get_help needs a policy

This tool retrieves documentation and help information, which is a read-only operation with no impact on system state, data integrity, or external operations. The minimal blast radius if misused by an agent is consulting potentially detailed technical information, which poses negligible security risk compared to other tools on this server that manage images, workflows, and scanners.

From the tool's definition Tool name 'get_help' and description 'Contextual documentation for OCR operations and tool configurations' indicate retrieval of informational content only. No side effects, modifications, deletions, executions, or financial operations are implied.

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

POLICY

How to control get_help

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

policy.json

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

get_help 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 OCR-MCP — 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 OCR-MCP tools

Execute execute_agentic_workflow execute_agentic_workflow Execute operate_scanner operate_scanner Execute process_document process_document Write manage_corpus manage_corpus Write manage_image manage_image Write manage_workflow manage_workflow Read get_status Real-time system health, backend availability, and resource utilization.

All 8 OCR-MCP 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 get_help

What does the get_help tool do? +

Contextual documentation for OCR operations and tool configurations. It is categorised as a Read tool in the OCR-MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_help? +

Register the OCR- MCP server in PolicyLayer and add a rule for get_help: 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 OCR-MCP. Nothing to install.

What risk level is get_help? +

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

Can I rate-limit get_help? +

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

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

get_help is provided by the OCR- MCP server (sandraschi/ocr-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every OCR-MCP tool call.

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

CHECK YOUR STACK →