Skip to main content
Glama
deenesjakoruzh
cjwpenner

MD-DOCX Converter

by cjwpenner
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

MD-DOCX Converter

A Python tool for bidirectional conversion between Markdown (.md) and Microsoft Word (.docx). Designed to make it easy to move content between Word documents and AI tools like Claude, ChatGPT, and GitHub Copilot.

What it does

  • Converts .md → .docx with correct heading hierarchy (Title, Heading 1–9)

  • Converts .docx → .md as clean GitHub Flavored Markdown (GFM)

  • Runs from a simple desktop shortcut — no command line knowledge needed

  • Handles headings, bold/italic/strikethrough, lists, task lists, tables, blockquotes, code blocks, images, and hyperlinks

  • Exports Mermaid diagrams (fenced code blocks) to high-quality, centered PNG images (rendered locally and offline)

See MarkdownSyntax.md for the full element mapping and notes on what is preserved, approximated, or dropped.

Related MCP server: Document Reading and Converter Tool

Requirements

  • Windows 10/11

  • Python 3.11+

  • The following Python packages (installed via pip):

pip install markdown-it-py python-docx

Optional (for offline Mermaid diagram rendering)

To enable local, offline rendering of Mermaid diagrams inside the generated Word documents without sending any diagram code to the internet, install:

pip install mermaidx

(Alternatively, if mmdc (Mermaid CLI) is on your system path, it will be used. If neither is available, diagrams are kept as plain monospaced code blocks with a warning).

Setup

1. Clone the repository

git clone https://github.com/cjwpenner/md-docx-converter.git
cd md-docx-converter

2. Install dependencies

pip install markdown-it-py python-docx
# Optional: for offline Mermaid diagram rendering support
pip install mermaidx

3. Create the desktop shortcut

pip install pywin32
python create_shortcut.py

This creates an MD-DOCX Converter shortcut on your Windows desktop. pywin32 is only needed to create the shortcut — it is not required to run the converter itself.

4. Run the converter

Double-click MD-DOCX Converter on your desktop. A console window opens and prompts:

MD ↔ DOCX Converter
--------------------
Enter file path:

Paste or type the full path to your .md or .docx file and press Enter. The converted file is saved in the same directory with the extension swapped.

You can also run directly from the command line:

python md_docx_converter/converter.py

Conversion notes

Heading hierarchy

The heading level mapping is context-dependent:

  • MD → DOCX: If there is exactly one # in the document, it becomes a Word Title. All other headings shift down by one level. If there are multiple # headings, they all become Heading 1 with no Title.

  • DOCX → MD: If the document has a Title style, it becomes #. All headings shift up accordingly. If there is no Title, Heading 1 becomes #.

Lossy elements

Word formatting that has no Markdown equivalent is approximated as bold:

Word formatting

Markdown output

Underline

**bold**

Highlight

**bold**

Small caps

**bold**

Font colour

Stripped (text kept)

Images

  • DOCX → MD: Embedded images are extracted to a {filename}_images/ folder next to the output .md file.

  • MD → DOCX: Images referenced by relative path are re-embedded. Missing images become [image not found: path].

Mermaid Diagrams

  • MD → DOCX: Code fences with language mermaid are converted to centered PNG diagrams locally and embedded in the document. This is 100% local and offline, keeping your sensitive data private.

Claude Code integration

This tool integrates with Claude Code as either a plugin (recommended — gets everything in two commands) or a standalone MCP server (for manual setup or Claude Desktop).

Option A: Claude Code plugin (recommended)

The plugin bundles the MCP server configuration and a /md-docx-converter:convert skill. Run these two commands inside Claude Code:

/plugin marketplace add cjwpenner/md-docx-converter
/plugin install md-docx-converter@md-docx-converter

That is it — no further configuration needed. After running /reload-plugins, Claude gains the conversion tools and you can invoke the skill directly:

/md-docx-converter:convert path/to/file.md
/md-docx-converter:convert path/to/report.docx

Or just ask naturally: "Convert this to a Word document" and Claude will use the tools automatically.

Option B: MCP server only (manual setup)

Use this if you want just the MCP tools without the plugin, or if you are configuring Claude Desktop rather than Claude Code.

Install the package:

pip install mcp-md-docx

Claude Code — register the MCP server:

claude mcp add md-docx-converter --transport stdio -- uvx mcp-md-docx

Claude Desktop — add to %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "md-docx-converter": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-md-docx"]
    }
  }
}

Tools exposed

Tool

What it does

read_docx

Read a .docx file — returns full Markdown text to the AI

write_docx

Create a .docx from Markdown text the AI has written

convert_md_file_to_docx

Convert a .md file on disk to .docx

convert_docx_file_to_md

Convert a .docx file on disk to .md

Once configured, you can say things like:

  • "Read report.docx and summarise it"

  • "Turn this into a Word document and save it to my Desktop"

  • "Convert all the bullet points in notes.docx into a table"

Project structure

md_docx_converter/
├── converter.py       # CLI entry point
├── md_to_docx.py      # Markdown → Word conversion
├── docx_to_md.py      # Word → Markdown conversion
├── heading_mapper.py  # Heading hierarchy pre-scan logic
├── image_handler.py   # Image extraction and embedding
└── launch.pyw         # Desktop shortcut launcher
mcp_md_docx/
├── server.py          # MCP server (four tools)
└── __main__.py        # Entry point for python -m mcp_md_docx
create_shortcut.py     # One-time shortcut setup script
pyproject.toml         # PyPI packaging config

License

This project is licensed under the GNU General Public License v3.0 (GPLv3). You are free to use, modify, and distribute this software, provided that any derivative works are also distributed under the same licence.

See LICENSE for the full licence text.

Third-party libraries

This project depends on the following open source libraries, all MIT-licensed:

Library

Purpose

Licence

mcp

Model Context Protocol server framework

MIT

markdown-it-py

GitHub Flavored Markdown parser

MIT

python-docx

Read and write Word .docx files

MIT

Full licence texts are reproduced in THIRD_PARTY_NOTICES.md.

Available Tools

4 tools
convert_docx_file_to_mdA

Convert a Word (.docx) file to a Markdown (.md) file. The output is saved alongside the input file. Returns the Markdown content.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses key behaviors: output file location (saved alongside input) and return value (Markdown content). However, it doesn't mention error handling, file size limits, format compatibility, or permission requirements, leaving gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero waste: first states core function, second adds crucial behavioral details (output location and return value). It's front-loaded with the primary purpose and efficiently covers additional context without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (file conversion), no annotations, and an output schema (which handles return values), the description is mostly complete. It covers purpose and key behaviors but lacks parameter details and some operational constraints, leaving minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It doesn't explain the 'path' parameter at all—no details on format, expected input type, or constraints. The description adds no parameter semantics beyond what the bare schema provides, failing to address the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action (convert), source format (.docx), target format (.md), and distinguishes from siblings like convert_md_file_to_docx (reverse operation) and read/write_docx (different actions). It precisely defines the tool's function without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (converting Word to Markdown) but doesn't explicitly state when to use this vs. alternatives like convert_md_file_to_docx or read_docx. It provides clear operational context but lacks explicit guidance on tool selection or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

convert_md_file_to_docxA

Convert a Markdown (.md) file to a Word (.docx) file. The output is saved alongside the input file with the same name and .docx extension.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses the output location behavior (saved alongside input with same name and .docx extension), which is valuable. However, it doesn't mention error handling, file size limits, formatting preservation, or authentication requirements that might be relevant for a file conversion tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero waste. First sentence states the core purpose, second sentence provides crucial behavioral detail about output location. Perfectly front-loaded and appropriately sized for this simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (which handles return values), a single parameter, and no annotations, the description is reasonably complete. It covers the conversion purpose and output location behavior. However, for a file operation tool, additional context about error conditions or limitations would make it more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% (parameter 'path' has no description in schema), so the description must compensate. While it doesn't explicitly explain the 'path' parameter, the context makes it clear this should be the path to a Markdown file. The description adds meaning by specifying the file type (.md) and the conversion outcome, though it could be more explicit about parameter expectations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action (convert), source format (Markdown .md file), and target format (Word .docx file). It distinguishes from sibling tools like convert_docx_file_to_md (reverse conversion) and read_docx/write_docx (different operations).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool (converting from Markdown to Word format). It doesn't explicitly state when not to use it or name specific alternatives, but the sibling tool names make the distinction obvious (e.g., use convert_docx_file_to_md for reverse conversion).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_docxA

Read a Word (.docx) document and return its full content as Markdown text. Use this when the user asks you to read, summarise, edit, or work with a Word document.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses the tool's behavior by stating it reads and returns content as Markdown, but lacks details on error handling, file size limits, or performance aspects. It adds basic context but does not fully compensate for the absence of annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose in the first sentence, followed by usage guidelines in the second. Both sentences are essential and waste no words, making it highly efficient and easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (one parameter) and the presence of an output schema (which handles return values), the description is mostly complete. It covers purpose and usage well but could benefit from more behavioral details like error cases or limitations to fully compensate for the lack of annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 0%, so the description must compensate. It implies the 'path' parameter is for the document location but does not specify format or constraints. With only one parameter, the baseline is high, and the description adds some meaning by linking it to Word documents, though more detail would improve clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Read a Word (.docx) document') and the resource type, with a precise outcome ('return its full content as Markdown text'). It distinguishes from siblings like 'convert_docx_file_to_md' by emphasizing reading rather than conversion, and from 'write_docx' by focusing on input rather than output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool ('when the user asks you to read, summarise, edit, or work with a Word document'), which covers common scenarios. However, it does not specify when not to use it or mention alternatives like 'convert_docx_file_to_md' for different purposes, leaving some ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

write_docxA

Convert Markdown text to a Word (.docx) document and save it to disk. Use this when the user asks you to create or save a Word document from text or Markdown content. The output_path should be an absolute path ending in .docx.

ParametersJSON Schema
NameRequiredDescriptionDefault
markdownYes
output_pathYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool saves to disk (a behavioral trait) and specifies the output path format, but lacks details on error handling, file overwriting behavior, or performance characteristics. It adequately covers the core action but misses some operational nuances.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by usage guidance and parameter specifics in three concise sentences. Each sentence adds value without redundancy, making it efficient and well-structured for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (2 parameters, no annotations, but has an output schema), the description is mostly complete. It covers purpose, usage, and parameter semantics adequately. The output schema likely handles return values, so the description doesn't need to explain those. Minor gaps remain in behavioral details like error handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate. It explains that 'markdown' is the input text and 'output_path' should be an absolute path ending in .docx, adding crucial semantic context beyond the bare schema. However, it doesn't detail markdown formatting support or path validation rules.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Convert Markdown text to a Word (.docx) document and save it to disk') and distinguishes it from siblings like 'convert_md_file_to_docx' (which likely processes files rather than text) and 'read_docx' (which reads rather than writes). It uses precise verbs and specifies the resource type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool ('when the user asks you to create or save a Word document from text or Markdown content'), providing clear context for its application. It also implies differentiation from siblings by focusing on text input rather than file processing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation2/5

The tools have significant overlap in purpose, particularly between convert_docx_file_to_md and read_docx (both convert DOCX to Markdown), and between convert_md_file_to_docx and write_docx (both convert Markdown to DOCX). The descriptions attempt to differentiate use cases (file conversion vs. content reading/writing), but an agent could easily misselect between these pairs due to unclear functional boundaries.

Naming Consistency4/5

The tool names follow a consistent verb_noun pattern with snake_case throughout (e.g., convert_docx_file_to_md, read_docx). The only minor deviation is that some names include 'file' while others do not, but overall the naming is predictable and readable.

Tool Count3/5

With 4 tools, the count is reasonable for a conversion-focused server, but it feels borderline thin given the overlapping functionality. A more streamlined set might have 2-3 tools instead, as the current count includes redundancy that doesn't add clear value to the surface.

Completeness4/5

For a DOCX-Markdown conversion domain, the tools cover the core bidirectional conversion operations and basic file handling. However, there are minor gaps, such as no tool for editing or manipulating the content in between conversions, which agents might need to work around by combining tools or external processing.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cjwpenner/md-docx-converter'

If you have feedback or need assistance with the MCP directory API, please join our Discord server