mcpField
W
Word Editing MCP Server

Word Editing MCP Server

Local
github.com/KS-GEN-AIProductivity2Updated 77w ago

About Word Editing MCP Server

A TypeScript MCP server for working with Microsoft Word files. It supports reading, replacing, and deleting .docx files, plus PDF conversion that preserves formatting and images.

Key features

  1. 01List folder contents
  2. 02Read .docx text
  3. 03Replace text and save a copy
  4. 04Delete Word files
  5. 05Convert to formatted PDF

Use cases

  1. 01Browse documents in a folder
  2. 02Extract text from Word files
  3. 03Replace words in a document
  4. 04Convert Word files to PDF

MCP support

Exposes tools for Word file operations and PDF conversion to MCP clients. File operations accept absolute or relative paths; PDF conversion requires LibreOffice.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Word Editing MCP Server

This server provides tools for interacting with Microsoft Word (.docx) files and converting them to PDF with precise formatting.

This is a TypeScript-based MCP server that provides tools to interact with Word files. It demonstrates core MCP concepts by providing:

  • Tools for reading, modifying, and deleting Word files
  • Tools for converting Word files to PDF (with full formatting)
  • All file and folder operations now work directly with absolute or relative paths (relative to the process current working directory). There is no longer any concept of a pre-selected working folder.

Features

Word Tools

list_files_in_folder
  • Purpose: List files in a given folder.
  • Parameters: folderPath (optional, absolute or relative path to the folder; if omitted, uses the current working directory).
read_word_content
  • Purpose: Read the text content of a Word (.docx) file.
  • Parameters: filePath (absolute or relative path to the .docx file).
replace_word_words
  • Purpose: Replace words in a Word (.docx) file and save as a new file.
  • Parameters:
    • filePath (input file, absolute or relative path)
    • outputFilePath (output file, absolute or relative path)
    • replacements (array of {from, to})
delete_word_file
  • Purpose: Delete a Word (.docx) file.
  • Parameters: filePath (absolute or relative path to the .docx file).
word_to_pdf
  • Purpose: Convert a Word (.docx) file to PDF, preserving all formatting and images. Requires LibreOffice installed.
  • Parameters:
    • filePath (input .docx, absolute or relative path)
    • outputFilePath (output .pdf, absolute or relative path)
  • Note: This uses LibreOffice in headless mode for professional-quality conversion. If LibreOffice is not installed, see the installation section below.

Installation complète

Installe les dépendances Node.js :

npm install

Installe LibreOffice (pour la conversion Word → PDF) :

npm run install-libreoffice

Compile le serveur :

npm run build

Pour le développement avec auto-rebuild :

npm run watch

Utilisation avec Claude Desktop

Ajoute la config suivante dans :

Sur MacOS : ~/Library/Application Support/Claude/claude_desktop_config.json Sur Windows : %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "Word Editing Server": {
      "command": "node",
      "args": [
        "/PATH_TO_THE_PROJECT/build/index.js"
      ],
      "env": {
      }
    }
  }
}

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.