// SCAN REPORT

Docx

9 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

6 can modify or destroy data

3 read-only

9 tools total

Community server · catalogue entry verified 29/06/2026

How to control Docx ↓

TOOL MAP

What Docx exposes to your agents

Read (3) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Docx tools

Write · Medium add_heading This tool creates or modifies document content (heading) without deleting or overwriting existing data irreversibly. Write · Medium add_image Adding an image to a Word document is a content modification that creates or alters data reversibly. Write · Medium add_paragraph Adding a paragraph to a document is a reversible write operation that creates or modifies data without destroying information. Write · Medium add_table The tool creates or modifies document structure by adding a table to a .docx file.

6 of Docx's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Docx

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

Rate limit write operations

{
  "add_heading": {
    "limits": [
      {
        "counter": "add_heading_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "extract_images": {
    "limits": [
      {
        "counter": "extract_images_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Docx — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DOCX →

Instant setup, no code required.

FULL CATALOGUE

All 9 Docx tools

WRITE 6 tools

Write add_heading Add a heading. Write add_image Add an image. Write add_paragraph Add a text paragraph. Write add_table Add a table. Write create_new_document Create a new empty Docx document. Write save_document Save the current document.

READ 3 tools

Read extract_images Extract images from the current document to a directory. Read get_document_structure Get the structure of the current document. Read load_document Load an existing Docx document.

FAQ

Questions about Docx

How do I prevent bulk modifications through Docx? +

The Docx server has 6 write tools including add_heading, add_image, add_paragraph. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Docx.

How many tools does the Docx MCP server expose? +

9 tools across 2 categories: Read, Write. 3 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Docx? +

Register the Docx MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Docx tool call.

Deterministic rules across all 9 Docx tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DOCX →

Instant setup, no code required.

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