Word MCP Server is an MCP server that enables users to create, open, and modify Microsoft Word (.docx) documents directly through Model Context Protocol clients. Built on Python using FastMCP and the python-docx library, it connects large language models directly to document generation workflows. Software developers, administrative professionals, and content creators use this tool to automate repetitive reporting and formatting tasks. By exposing document actions as standardized tools, the server allows AI models to generate complex Word files from natural language prompts. It supports adding headings of varying hierarchy levels, formatting paragraphs with customized font sizes and alignments, applying bold or colored run-level styling, highlighting text, inserting images from file paths or numpy arrays via OpenCV, and building structured multi-column tables. Once changes are made, the server can save the output directly to the local filesystem, simplifying end-to-end document publishing pipelines.
Category: CRM, ERP & E-commerce
Tags: document automation, docx, microsoft word, office
bash uv venv source venv/bin/activate 3. Install the dependencies in the repository directory: bash uv pip install . 4. Add the server to your MCP configuration file (such as Claude Desktop's config): json { "mcpServers": { "word-mcp-server": { "command": "/path/to/word-mcp-server/.venv/bin/python3", "args": ["/path/to/word-mcp-server/server.py"] } } } 5. Replace /path/to/word-mcp-server/ with the absolute path to your virtual environment and server.py script, then restart your MCP client.Part of MCP Servers
You need Python 3.12 or newer. Clone the repository, create a virtual environment with uv venv, activate it, and run uv pip install . to install required dependencies including python-docx, opencv-python, numpy, and FastMCP.
The server enables LLMs to create new Microsoft Word documents or open existing ones. It exposes tools to insert headings, add paragraphs with text formatting, apply colors and highlights, embed images from files or arrays, and construct tables.
Word MCP Server works with any standard Model Context Protocol client that supports local command-line servers, including Claude Desktop, Cursor, and OtterMind, by configuring the path to the Python environment and server script.
Word MCP Server supports inserting images into Word documents either directly by specifying the file path on disk or by passing an image matrix via OpenCV and numpy.