Convert DOCX file to HTML with formatting preserved
AI agents call convert_to_html 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.
The tool reads a DOCX document and converts its content to HTML format. It does not write, delete, execute, or perform any financial operations. It is a pure transformation/extraction operation similar to the sibling tools (extract_text, convert_to_markdown), all of which are read-only in nature.
From the tool's definition 'Convert DOCX file to HTML with formatting preserved' — this is a read/transform operation that reads an existing DOCX file and produces HTML output, with no side effects or data modification.
Attacks that exploit this kind of access
Convert DOCX file to HTML with formatting preserved. 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 convert_to_html: 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.
convert_to_html 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 convert_to_html 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 convert_to_html. 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.
convert_to_html 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 →