Save every embedded image to disk. Args: file_path, output_dir (optional; defaults to <file>_images/).
AI agents call extract_hwp_images to retrieve information from Hwp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool extracts and saves images from HWP files to disk, which is a read operation that retrieves data without altering the document itself. While it writes image files to the filesystem, this is incidental data export rather than modification of the document structure or content. No data is deleted, overwritten, or irreversibly changed in the HWP file.
From the tool's definition Tool name 'extract_hwp_images' and description 'Save every embedded image to disk' indicates retrieval/extraction of embedded data with no modification to the source document.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access extract_hwp_images 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 extract_hwp_images:
{
"version": "1",
"default": "deny",
"tools": {
"extract_hwp_images": {}
}
}extract_hwp_images is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Save every embedded image to disk. Args: file_path, output_dir (optional; defaults to <file>_images/). It is categorised as a Read tool in the Hwp MCP Server, which means it retrieves data without modifying state.
Register the Hwp MCP server in PolicyLayer and add a rule for extract_hwp_images: 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.
extract_hwp_images is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the extract_hwp_images 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 extract_hwp_images. 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.
extract_hwp_images 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.
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.