Create a new minimal .hwpx file with optional title and body text. Args: - output_path (string): Absolute path to save the new .hwpx file - title (string, optional): Document title metadata - content (string, optional): Initial body text Returns: {
AI agents use hwpx_create 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.
hwpx_create generates a new .hwpx file on the filesystem based on provided arguments. This is a Write operation—it creates data reversibly (the file can be deleted or modified later). Severity is medium rather than low because an agent could create files at arbitrary paths specified by output_path, potentially filling disk space or overwriting files in critical locations depending on permissions and path resolution.
From the tool's definition Tool description states 'Create a new minimal .hwpx file' with parameters for output_path, title, and content. This creates new data in the form of a document file.
Attacks that exploit this kind of access
Create a new minimal .hwpx file with optional title and body text. Args: - output_path (string): Absolute path to save the new .hwpx file - title (string, optional): Document title metadata - content (string, optional): Initial body text Returns: {. 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 hwpx_create: 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.
hwpx_create 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 hwpx_create 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 hwpx_create. 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.
hwpx_create is provided by the Hwpx MCP server (rgbcap/hwpx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →