Extract and list images from a DOCX file
AI agents call extract_images to retrieve information from DOCX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves image data from a Word document. There are no side effects, data modifications, deletions, code execution, or financial implications. Extracting images is a passive data retrieval operation analogous to searching or fetching content. Even if an agent extracts sensitive images, the tool itself does not modify or delete them, making this a Read category risk.
From the tool's definition Tool name is 'extract_images' and description states it will 'Extract and list images from a DOCX file' — these are read-only operations that retrieve data without modification.
Attacks that exploit this kind of access
Extract and list images from a DOCX file. It is categorised as a Read tool in the DOCX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DOCX MCP Server MCP server in PolicyLayer and add a rule for extract_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 DOCX MCP Server. Nothing to install.
extract_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_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_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_images is provided by the DOCX MCP Server MCP server (zeph-gh/docx-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 →