This record as markdown: /tools/airmang-hwpx-mcp-server/apply-edit.md
What apply_edit does on Hwpx
AI agents use apply_edit to create or update resources in Hwpx, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hwpx environment.
Why apply_edit is rated Medium
The tool applies edits to HWPX documents based on validation plans. Although it claims not to modify the original directly, it still creates or modifies document content, which is characteristic of Write operations. The high severity reflects that an agent could apply unintended validation plans to create malformed documents or corrupt formatting.
From the tool's definition Tool description indicates it 'applies validation plan' and explicitly states '원본 HWPX는 직접 수정하지 않습니다' (does not directly modify original HWPX), suggesting reversible modification of document content based on a validation plan.
Attacks that exploit this kind of access
The rule that runs apply_edit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hwpx, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For apply_edit, this is the rule to start with:
apply_edit 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Hwpx, apply this rule, and every apply_edit call is checked against it from then on.
Questions about apply_edit
[고급] 검증 계획을 적용합니다. 원본 HWPX는 직접 수정하지 않습니다. It is categorised as a Write tool in the Hwpx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hwpx MCP server in PolicyLayer and add a rule for apply_edit: 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 Hwpx. Nothing to install.
apply_edit 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 apply_edit 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 apply_edit. 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.
apply_edit is provided by the Hwpx MCP server (airmang/hwpx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hwpx, and thousands of servers like it.
This server
Across the catalogue