MCP.so
Sign In
Servers

Word MCP Server

@MCP-Mirror

Mirror of

Overview

What is Word MCP Server?

Word MCP Server is a Python application that enables creating and editing Microsoft Word (.docx) documents through an API using FastMCP. It provides tools for interacting with Word documents, such as adding text, images, and tables. It is designed for developers and LLMs needing programmatic document generation.

How to use Word MCP Server?

Install dependencies with uv pip install . after creating a virtual environment. Configure it for an LLM by providing a JSON object with the path to the Python interpreter and the server.py script. Once running, the server accepts commands from the LLM to create or edit documents using natural language or direct API calls.

Key features of Word MCP Server

  • Create and open Word documents
  • Add and format text (headings, paragraphs, runs)
  • Insert images from file paths or numpy arrays
  • Create tables with custom styles and data
  • Manage resources and prompts for document workflows

Use cases of Word MCP Server

  • Automate report generation with dynamic content
  • Enable LLMs to produce formatted Word documents from natural language prompts
  • Batch create documents with consistent structure and styling

FAQ from Word MCP Server

What dependencies does Word MCP Server require?

It requires Python 3.12+, and the libraries python-docx, opencv-python, numpy, and FastMCP.

How do I configure Word MCP Server for an LLM?

Provide a JSON configuration with the command pointing to the Python interpreter in the virtual environment and args including the path to server.py.

What colors are supported for text and highlights?

Supported colors include black, blue, green, dark blue, dark red, dark yellow, dark green, pink, red, white, teal, yellow, violet, gray25, and gray50.

Can I add images from numpy arrays?

Yes, you can add images using a numpy array (e.g., from OpenCV) with the add_picture function.

Does Word MCP Server store resources and prompts?

Yes, resources and prompts are stored in the resources and prompts directories within the project.

More from Other