AI agents call get_document_structure to retrieve information from Docx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about a document's structure (headings, sections, organization) without creating, modifying, deleting, or executing any operations. It is a pure read operation with no side effects, fitting the Read category. Severity is low because accessing document structure poses minimal risk—the worst case is information disclosure of document organization, which is relatively benign.
From the tool's definition Tool name 'get_document_structure' and description 'Get the structure of the current document' indicate a retrieval operation that queries document metadata/layout without modification.
Attacks that exploit this kind of access
Get the structure of the current document. It is categorised as a Read tool in the Docx MCP Server, which means it retrieves data without modifying state.
Register the Docx MCP server in PolicyLayer and add a rule for get_document_structure: 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. Nothing to install.
get_document_structure 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 get_document_structure 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 get_document_structure. 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.
get_document_structure is provided by the Docx MCP server (okamifeng/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 →