Word

Provides a local MCP server that converts AI-generated content into downloadable Word documents with markdown support, headers, tables, and metadata.

javascript

0

GitHub Stars

javascript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mokhtarlahjaily-word-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-v",
        "$(pwd)/generated_reports:/app/output",
        "word-mcp"
      ],
      "env": {
        "OUTPUT_DIR": "./generated_reports"
      }
    }
  }
}

Word MCP is a factory-style MCP server that converts AI-generated text and data into professional Word documents (.docx) by generating files directly on your host. It supports structured content, Markdown-to-Word formatting, and rich elements like headers, tables, and metadata, making it easy to produce polished documents from your AI workflows.

How to use

Set up your MCP client to connect to the Word MCP server and generate documents that your users can download. The server operates locally and via Docker, and it saves the final Word files to a mapped output folder on your host. You can instruct the AI to provide a document title, sections with headings, tables, and metadata, and the server will assemble these into a .docx file.

Typical workflows include: issuing a generate request with a filename, a document title, and an array of sections. Each section can have a heading, content in paragraphs, and optional tables with headers and rows. The server also supports basic Markdown formatting so bold text and lists translate into Word styling.

How to install

Prerequisites you need before running Word MCP are Node.js and Docker. Ensure your environment can run containers and host files.

# Prerequisites: Node.js and Docker
node -v
docker -v

Additional setup and configuration

The server writes generated Word files to a local directory. You can control this directory with an environment variable when running it in development mode.

# Local development: optional output directory
export OUTPUT_DIR=./generated_reports

Notes on running with Docker

To make the generated documents accessible from your host, run the container with a volume mapped to your output folder.

# Build the image
docker build -t word-mcp .

# Run with volume mapping to your output directory
docker run --rm -i -v $(pwd)/generated_reports:/app/output word-mcp

Troubleshooting

If you do not see the generated files, verify the volume mapping and permissions of the host folder. The container runs with the typical user context and needs write access to the mapped directory.

Examples of usage scenarios

Create a project report with a title, an executive section, and a data table. The AI provides structured content; Word MCP converts it into a formatted document and saves it to your output folder.

Available tools

generate_report

Create a complete Word document in one step, including title, sections, and metadata.

markdown_support

Automatically convert basic Markdown formatting (bold, lists) into Word styling during document generation.

headers

Support headers at levels 1–3 for document structure.

tables

Include data tables with custom headers and rows.

paragraphs

Add text paragraphs as part of sections.

metadata

Attach file metadata such as title and author to the document.