mcp-markdown-to-docx
Enables AI agents to convert Markdown into styled Word (.docx) documents, with control over fonts, colors, and layout via parameters.
README
📄 MCP Markdown to DOCX Server
An MCP (Model Context Protocol) server that empowers your AI agents (like Claude Desktop or Cursor) to autonomously generate beautifully styled, production-ready Microsoft Word (.docx) documents from Markdown.
🌟 The Concept: AI-Driven Document Formatting
Most AI agents can write text, but delivering a finished, clean, and properly formatted file is often a manual secondary step.
This MCP server bridges that gap. It gives your AI the ability to not only write your content but also fully control document styling. When the AI uses this tool, it can decide on fonts, header colors, margins, and typography directly through parameters. The result? A perfectly formatted Word document saved directly to your local drive, ready to be sent or presented.
No more copy-pasting raw text into Word and manually tweaking headers. Let the AI do the secretarial work.
✨ Features
- Markdown to DOCX Conversion: Seamlessly translates standard Markdown (including tables, lists, and code blocks) into native Word elements.
- Autonomous Styling: AI agents can dynamically inject style settings (
font_family,h1_color,body_size_pt, etc.) via JSON parameters. - Local File Saving: Generates the
.docxfile and saves it securely to your local machine (or any designated directory). - FastMCP Integration: Built using the official
mcpPython SDK for robuststdiocommunication with clients like Claude Desktop.
🚀 Installation
Option 1: Using uv (Recommended)
You don't even need to install it manually. Just use uvx:
uvx mcp-markdown-to-docx
Option 2: Standard Python installation
-
Clone the repository:
git clone https://github.com/Baptiste4321/mcp-markdown-to-docx.git cd mcp-markdown-to-docx -
Install the package: Ensure you have Python 3.10 or higher installed.
pip install .
⚙️ Configuration (Claude Desktop)
To connect this tool to Claude Desktop, add the following configuration to your claude_desktop_config.json file.
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"markdown-to-docx": {
"command": "uvx",
"args": [
"mcp-markdown-to-docx"
],
"env": {
"MARKDOWN_API_URL": "https://markdown-to-docx.pfoly.com"
}
}
}
}
Note: If you installed it manually via pip instead of uv, change the command to
mcp-markdown-to-docxand remove the args.
💬 Example Prompts
Once configured, simply talk to your AI Agent:
"Write a comprehensive report about the impact of AI on modern healthcare. Format the output as a Word document, use 'Montserrat' font, and make all main headers dark blue. Save it to my Desktop."
"Take these rough meeting notes, expand them into a professional meeting minutes document, and generate a DOCX file named 'Q3_Meeting_Minutes'."
📜 License
MIT License. Feel free to fork and modify!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.