Correct one local HWPX/HWP document and optionally write a markdown report.
AI agents use correct_document to create or update resources in GongMun Doctor MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GongMun Doctor MCP environment.
This is a Write operation because it creates or modifies data reversibly. The tool applies corrections to Korean documents, which involves writing changes back to the file system.
From the tool's definition The tool description states it can 'correct' and 'optionally write a markdown report' to a document. This involves modifying the original document (the HWPX/HWP file) with corrections applied by the AI system.
Documented attack patterns abuse exactly the kind of access correct_document gives an agent:
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 correct_document:
{
"version": "1",
"default": "deny",
"tools": {
"correct_document": {
"limits": [
{
"counter": "correct_document_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}correct_document 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.
Free to start. No card required.
Correct one local HWPX/HWP document and optionally write a markdown report. It is categorised as a Write tool in the GongMun Doctor MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GongMun Doctor MCP server in PolicyLayer and add a rule for correct_document: 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.
correct_document is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the correct_document 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.
Set action: deny in the PolicyLayer policy for correct_document. 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.
correct_document 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.
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.
Free to start. No card required.
10 GongMun Doctor MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.