This record as markdown: /tools/securityronin-docx-mcp/diff-to-text.md
What diff_to_text does on Docx
AI agents call diff_to_text to retrieve information from Docx without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why diff_to_text is rated Low
The name 'diff_to_text' implies generating a textual representation of differences, which is a read-only operation. However, the description is empty, lowering confidence. In the context of a Word document MCP server focused on track changes and OOXML manipulation, this tool likely reads document differences and returns them as text. No destructive or write behavior is implied by the name alone.
From the tool's definition Tool name 'diff_to_text' suggests converting a diff to text output, which is a read/transform operation with no side effects.
Attacks that exploit this kind of access
The rule that runs diff_to_text safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Docx, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For diff_to_text, this is the rule to start with:
diff_to_text is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Docx, apply this rule, and every diff_to_text call is checked against it from then on.
Questions about diff_to_text
diff_to_text is a read tool on the Docx MCP server. 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 diff_to_text: 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.
diff_to_text 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 diff_to_text 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 diff_to_text. 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.
diff_to_text is provided by the Docx MCP server (securityronin/docx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Docx, and thousands of servers like it.
This server
Across the catalogue