# DOCX Document Processor

> Use this tool when you need to process DOCX documents programmatically, extracting text, converting to HTML or Markdown, and analyzing document structure while preserving formatting. It solves problems related to document processing workflows, content migration, and building AI assistants that require access to Word document content. The tool takes DOCX files as input and outputs extracted text, converted HTML or Markdown, document statistics, and extracted images, making it ideal for automating document tasks and integrating with AI systems.

Canonical page: https://skillsregistry.net/skills/zeph-gh-docx-processor  
JSON: https://api.skillsregistry.net/v1/skills/zeph-gh-docx-processor

## Description

This MCP server provides AI assistants with comprehensive DOCX document processing capabilities through the Mammoth library, offering tools for text extraction, HTML conversion with formatting preservation, Markdown conversion, document structure analysis, and image extraction. Built using TypeScript with the Model Context Protocol SDK and Mammoth for document parsing, it supports both plain text extraction and rich format conversion while maintaining document styling, headings, lists, and other formatting elements. The implementation includes document analysis features that provide statistics on word count, paragraph count, heading structure, and formatting elements like bold/italic text, plus image extraction capabilities that can either embed images as base64 or save them to specified directories, making it valuable for document processing workflows, content migration tasks, and building AI assistants that need programmatic access to Word document content without manual conversion.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/zeph-gh-docx-processor)
- **Repository:** <https://github.com/zeph-gh/docx-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zeph-gh-docx-processor"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zeph-gh-docx-processor` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zeph-gh-docx-processor/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt