MCP-Doc
A powerful Word document processing service based on FastMCP, enabling AI assistants to create, edit, and manage docx files with full formatting support.
Documentation
Docx MCP Service
A Docx document processing service based on the FastMCP library, supporting the creation, editing, and management of Word documents using AI assistants in Cursor.
Features
- Complete Document Operations: Support for creating, opening, saving documents, as well as adding, editing, and deleting content
- Formatting: Support for setting fonts, colors, sizes, alignment, and other formatting options
- Table Processing: Support for creating, editing, merging, and splitting table cells
- Image Insertion: Support for inserting images and setting their sizes
- Layout Control: Support for setting page margins, adding page breaks, and other layout elements
- Query Functions: Support for retrieving document information, paragraph content, and table data
- Convenient Editing: Support for find and replace functionality
- Section Editing: Support for replacing content in specific sections while preserving original formatting and styles
Installation Dependencies
Ensure Python 3.10+ is installed, then install the following dependencies:
pip3 install python-docx mcpUsage
Using as an MCP Service in Cursor
1. Open Cursor and go to Settings
2. Find the `Features > MCP Servers` section
3. Click `Add new MCP server`
4. Fill in the following information:
5. Click `Add` to add the service
After adding, you can use natural language to operate Word documents in Cursor's AI assistant, for example:
- "Create a new Word document and save it to the desktop"
- "Add a level 3 heading"
- "Insert a 3x4 table and fill it with data"
- "Set the second paragraph to bold and center-aligned"
Supported Operations
The service supports the following operations:
- Document Management: `create_document`, `open_document`, `save_document`
- Content Addition: `add_paragraph`, `add_heading`, `add_table`, `add_picture`
- Content Editing: `edit_paragraph`, `delete_paragraph`, `delete_text`
- Table Operations: `add_table_row`, `delete_table_row`, `edit_table_cell`, `merge_table_cells`, `split_table`
- Layout Control: `add_page_break`, `set_page_margins`
- Query Functions: `get_document_info`, `get_paragraphs`, `get_tables`, `search_text`
- File Operations: `create_document`, `open_document`, `save_document`, `save_as_document`, `create_document_copy`
- Section Editing: `replace_section`, `edit_section_by_keyword`
- Other Functions: `find_and_replace`, `search_and_replace` (with preview functionality)
How It Works
1. The service uses the Python-docx library to process Word documents
2. It implements the MCP protocol through the FastMCP library to communicate with AI assistants
3. It processes requests and returns formatted responses
4. It supports complete error handling and status reporting
Typography Capabilities
The service has good typography understanding capabilities:
- Text Hierarchy: Support for heading levels (1-9) and paragraph organization
- Page Layout: Support for page margin settings
- Visual Elements: Support for font styles (bold, italic, underline, color) and alignment
- Table Layout: Support for creating tables, merging cells, splitting tables, and setting table formats
- Pagination Control: Support for adding page breaks
Development Notes
- `server.py` - Core implementation of the MCP service using the FastMCP library
Troubleshooting
If you encounter problems in Cursor, try the following steps:
1. Ensure Python 3.10+ is correctly installed
2. Ensure the python-docx and mcp libraries are correctly installed
3. Check if the server path is correct
4. Restart the Cursor application
Notes
- Ensure the python-docx and mcp libraries are correctly installed
- Ensure Chinese characters in paths can be correctly processed
- Using absolute paths can avoid path parsing issues
License
MIT License
Frequently asked questions
What is MCP-Doc?
MCP-Doc is A powerful Word document processing service based on FastMCP, enabling AI assistants to create, edit, and manage docx files with full formatting support.
How do I install MCP-Doc?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is MCP-Doc open source?
Yes — it is hosted on GitHub at https://github.com/meterlong/mcp-doc and has 137 stars.
Related MCP tools
This MCP server integrates with your Google Drive and Google Sheets, to enable creating and modifying spreadsheets. Python-based implementation.
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to
🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP