preview_text_corrections

THE RISK

Low Risk

Why preview_text_corrections needs a policy

This tool performs a query/preview operation that returns correction suggestions without executing changes, creating files, deleting data, or triggering external operations. The explicit constraint that it does not touch files confirms its read-only nature.

From the tool's definition Tool 'preview_text_corrections' previews corrections to plain text without touching files. The description explicitly states it does not modify or persist data ('without touching files'), making it a read-only operation that retrieves suggested corrections…

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

POLICY

How to control preview_text_corrections

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

policy.json

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

preview_text_corrections 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 GongMun Doctor 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 GongMun Doctor MCP tools

Write correct_documents_in_folder Correct every local HWPX/HWP document in a folder. Write render_document_template Render a template with partial or complete variable values. Write correct_document Correct one local HWPX/HWP document and optionally write a markdown report. Read match_document_templates Return templates whose trigger keywords match the query. Read get_correction_report Read a previously generated markdown correction report. Read get_server_info Describe the currently exposed MCP surface and deferred areas. Read get_template_variables Show which variables are required to render a template. Read list_document_templates List bundled administrative templates, optionally filtered by category.

All 10 GongMun Doctor 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 preview_text_corrections

What does the preview_text_corrections tool do? +

Preview rule-based corrections for plain text without touching files. It is categorised as a Read tool in the GongMun Doctor MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on preview_text_corrections? +

Register the GongMun Doctor MCP server in PolicyLayer and add a rule for preview_text_corrections: 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 GongMun Doctor MCP. Nothing to install.

What risk level is preview_text_corrections? +

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

Can I rate-limit preview_text_corrections? +

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

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

preview_text_corrections is provided by the GongMun Doctor MCP server (sinmb79/gongmun-doctor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GongMun Doctor MCP tool call.

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

CHECK YOUR STACK →