Low Risk

read_part

Read raw XML of any DOCX part (e.g. 'word/document.xml').

How to control read_part ↓

What read_part does on Docx

AI agents call read_part 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.

Low Risk

Why read_part needs a policy

This tool retrieves and queries raw XML data from DOCX document parts with no side effects. It is a read-only operation that does not create, modify, delete, or execute code. The ability to read any part of the document structure has minimal blast radius—an AI agent misusing this would at worst over-access document internals, but cannot damage or alter the document.

From the tool's definition Tool name 'read_part' and description 'Read raw XML of any DOCX part' explicitly state retrieval of document content without modification or deletion.

Documented attack patterns abuse exactly the kind of access read_part gives an agent:

How to control read_part

PolicyLayer is an MCP gateway — it sits between your AI agents and Docx, and nothing reaches the server without passing your rules. This is the rule we recommend for read_part:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_part": {}
  }
}

read_part is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Docx — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about read_part

What does the read_part tool do? +

Read raw XML of any DOCX part (e.g. 'word/document.xml'). It is categorised as a Read tool in the Docx MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on read_part? +

Register the Docx MCP server in PolicyLayer and add a rule for read_part: 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.

What risk level is read_part? +

read_part is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit read_part? +

Yes. Add a rate_limit block to the read_part 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.

How do I block read_part completely? +

Set action: deny in the PolicyLayer policy for read_part. 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.

What MCP server provides read_part? +

read_part 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.

Enforce policy on every Docx tool call.

Start from Docx, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

219 Docx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.