Medium Risk

set_hwp_paragraph_text

Replace the entire text of the Nth paragraph (0-based) in an .hwpx body with new text. The paragraph attributes (paraPr/style refs) are preserved; runs are collapsed into a single <hp:run> with the new text. Args: file_path, index, text, output_path (optional).

How to control set_hwp_paragraph_text ↓

AI agents use set_hwp_paragraph_text to create or update resources in Hwp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hwp environment.

Medium Risk

This tool modifies document content by replacing paragraph text while preserving formatting. Although it alters data, the operation is reversible (the original text can be restored by writing different text), making it a Write operation rather than Destructive.

From the tool's definition The tool 'set_hwp_paragraph_text' replaces the entire text of a paragraph in an .hwpx file. The description explicitly states it modifies content: 'Replace the entire text of the Nth paragraph...with new text.' This is a reversible modification operation.

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

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_hwp_paragraph_text": {
      "limits": [
        {
          "counter": "set_hwp_paragraph_text_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

set_hwp_paragraph_text 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.

  1. Create a free account and register Hwp — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the set_hwp_paragraph_text tool do? +

Replace the entire text of the Nth paragraph (0-based) in an .hwpx body with new text. The paragraph attributes (paraPr/style refs) are preserved; runs are collapsed into a single <hp:run> with the new text. Args: file_path, index, text, output_path (optional). It is categorised as a Write tool in the Hwp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_hwp_paragraph_text? +

Register the Hwp MCP server in PolicyLayer and add a rule for set_hwp_paragraph_text: 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 Hwp. Nothing to install.

What risk level is set_hwp_paragraph_text? +

set_hwp_paragraph_text is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit set_hwp_paragraph_text? +

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

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

set_hwp_paragraph_text is provided by the Hwp MCP server (treesoop/hwp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Hwp tool call.

Deterministic rules across all 31 Hwp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

31 Hwp tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.