Office Word MCP Server
Office-Word-MCP-服务器
用于创建、读取和操作 Microsoft Word 文档的模型上下文协议 (MCP) 服务器。该服务器使 AI 助手能够通过标准化界面处理 Word 文档,并提供丰富的文档编辑功能。
概述
Office-Word-MCP-Server 实现了模型上下文协议 (MCP) ,将 Word 文档操作公开为工具和资源。它充当 AI 助手和 Microsoft Word 文档之间的桥梁,支持文档创建、内容添加、格式化和分析。
该服务器采用模块化架构,将关注点分为核心功能、工具和实用程序,使其具有高度的可维护性和可扩展性,以便在未来进行增强。
例子
提示
输出
Related MCP server: Claude Document MCP Server
特征
文档管理
使用元数据创建新的 Word 文档
提取文本并分析文档结构
查看文档属性和统计信息
列出目录中的可用文档
创建现有文档的副本
将多个文档合并为一个文档
将 Word 文档转换为 PDF 格式
内容创作
添加不同级别的标题
插入具有可选样式的段落
使用自定义数据创建表
添加按比例缩放的图像
插入分页符
向文档添加脚注和尾注
将脚注转换为尾注
自定义脚注和尾注样式
富文本格式
格式化特定的文本部分(粗体、斜体、下划线)
更改文本颜色和字体属性
将自定义样式应用于文本元素
在整个文档中搜索和替换文本
表格格式
使用边框和样式设置表格格式
创建具有不同格式的标题行
应用单元格底纹和自定义边框
构建表格以提高可读性
高级文档操作
删除段落
创建自定义文档样式
在整个文档中应用一致的格式
使用详细控制来格式化特定范围的文本
文档保护
为文档添加密码保护
使用可编辑部分实现限制编辑
向文档添加数字签名
验证文件的真实性和完整性
安装
先决条件
Python 3.8 或更高版本
pip 包管理器
基本安装
# Clone the repository
git clone https://github.com/GongRzhe/Office-Word-MCP-Server.git
cd Office-Word-MCP-Server
# Install dependencies
pip install -r requirements.txt使用安装脚本
或者,您可以使用提供的安装脚本来处理:
检查先决条件
设置虚拟环境
安装依赖项
生成 MCP 配置
python setup_mcp.py与 Claude 桌面版一起使用
配置
方法 1:本地安装后
安装后,将服务器添加到您的 Claude for Desktop 配置文件中:
{
"mcpServers": {
"word-document-server": {
"command": "python",
"args": ["/path/to/word_mcp_server.py"]
}
}
}方法二:无需安装(使用 uvx)
您还可以使用 uvx 包管理器将 Claude for Desktop 配置为使用服务器而无需本地安装:
{
"mcpServers": {
"word-document-server": {
"command": "uvx",
"args": ["--from", "office-word-mcp-server", "word_mcp_server"]
}
}
}配置文件位置:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
重新启动 Claude for Desktop 以加载配置。
示例操作
配置完成后,您可以要求 Claude 执行如下操作:
“创建一个名为‘report.docx’的新文档,并添加标题页”
“在我的文档中添加一个标题和三个段落”
“插入包含销售数据的 4x4 表格”
将第 2 段中的“重要”一词格式化为粗体和红色
“搜索并将所有‘旧术语’替换为‘新术语’”
“为章节标题创建自定义样式”
“将格式应用于我的文档中的表格”
API 参考
文档创建和属性
create_document(filename, title=None, author=None)
get_document_info(filename)
get_document_text(filename)
get_document_outline(filename)
list_available_documents(directory=".")
copy_document(source_filename, destination_filename=None)
convert_to_pdf(filename, output_filename=None)内容添加
add_heading(filename, text, level=1)
add_paragraph(filename, text, style=None)
add_table(filename, rows, cols, data=None)
add_picture(filename, image_path, width=None)
add_page_break(filename)内容提取
get_document_text(filename)
get_paragraph_text_from_document(filename, paragraph_index)
find_text_in_document(filename, text_to_find, match_case=True, whole_word=False)文本格式
format_text(filename, paragraph_index, start_pos, end_pos, bold=None,
italic=None, underline=None, color=None, font_size=None, font_name=None)
search_and_replace(filename, find_text, replace_text)
delete_paragraph(filename, paragraph_index)
create_custom_style(filename, style_name, bold=None, italic=None,
font_size=None, font_name=None, color=None, base_style=None)表格格式
format_table(filename, table_index, has_header_row=None,
border_style=None, shading=None)故障排除
常见问题
缺少样式
某些文档可能缺少标题和表格操作所需的样式
服务器将尝试创建缺失的样式或使用直接格式化
为获得最佳效果,请使用具有标准 Word 样式的模板
权限问题
确保服务器具有读取/写入文档路径的权限
使用
copy_document函数创建锁定文档的可编辑副本如果操作失败,请检查文件所有权和权限
图像插入问题
对图像文件使用绝对路径
验证图像格式兼容性(推荐 JPEG、PNG)
检查图像文件大小和权限
调试
通过设置环境变量启用详细日志记录:
export MCP_DEBUG=1 # Linux/macOS
set MCP_DEBUG=1 # Windows贡献
欢迎贡献代码!欢迎提交 Pull 请求。
分叉存储库
创建你的功能分支(
git checkout -b feature/amazing-feature)提交您的更改(
git commit -m 'Add some amazing feature')推送到分支(
git push origin feature/amazing-feature)打开拉取请求
执照
该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅 LICENSE 文件。
致谢
协议规范的模型上下文协议
用于 Word 文档操作的python-docx
FastMCP用于 Python MCP 实现
注意:此服务器会与您系统上的文档文件进行交互。请务必在 Claude for Desktop 或其他 MCP 客户端中确认请求的操作是否正确。
Available Tools
54 toolsadd_endnote_to_documentC
Add an endnote to a specific paragraph in a Word document.
Inputs: filename (required), paragraph_index (required), endnote_text (required).
add_footnote_after_textC
Add a footnote after specific text with proper superscript formatting. This enhanced function ensures footnotes display correctly as superscript.
Inputs: filename (required), search_text (required), footnote_text (required), output_filename.
add_footnote_before_textC
Add a footnote before specific text with proper superscript formatting. This enhanced function ensures footnotes display correctly as superscript.
Inputs: filename (required), search_text (required), footnote_text (required), output_filename.
add_footnote_enhancedC
Enhanced footnote addition with guaranteed superscript formatting. Adds footnote at the end of a specific paragraph with proper style handling.
Inputs: filename (required), paragraph_index (required), footnote_text (required), output_filename.
add_footnote_robustC
Add footnote with robust validation and Word compliance. This is the production-ready version with comprehensive error handling.
Inputs: filename (required), search_text, paragraph_index, footnote_text, +2 more.
add_footnote_to_documentC
Add a footnote to a specific paragraph in a Word document.
Inputs: filename (required), paragraph_index (required), footnote_text (required).
add_headingA
Add a heading to a Word document with optional formatting.
Args: filename: Path to Word document text: Heading text level: Heading level (1-9) font_name: Font family (e.g., 'Helvetica') font_size: Font size in points (e.g., 14) bold: Make heading bold italic: Make heading italic border_bottom: Add bottom border (for section headers)
Inputs: filename (required), text (required), level, font_name, +4 more.
add_page_breakC
Add a page break to the document.
Inputs: filename (required).
add_paragraphB
Add a paragraph to a Word document with optional formatting.
Args: filename: Path to Word document text: Paragraph text content style: Optional paragraph style name font_name: Font family (e.g., 'Helvetica', 'Times New Roman') font_size: Font size in points (e.g., 14, 36) bold: Make text bold italic: Make text italic color: Text color as hex RGB (e.g., '000000')
Inputs: filename (required), text (required), style, font_name, +4 more.
add_pictureC
Add an image to a Word document.
Inputs: filename (required), image_path (required), width.
add_tableC
Add a table to a Word document.
Inputs: filename (required), rows (required), cols (required), data.
apply_table_alternating_rowsC
Apply alternating row colors to a table for better readability.
Inputs: filename (required), table_index (required), color1, color2.
auto_fit_table_columnsC
Set table columns to auto-fit based on content.
Inputs: filename (required), table_index (required).
convert_to_pdfC
Convert a Word document to PDF format.
Inputs: filename (required), output_filename.
copy_documentC
Create a copy of a Word document.
Inputs: source_filename (required), destination_filename.
create_custom_styleC
Create a custom style in the document.
Inputs: filename (required), style_name (required), bold, italic, +4 more.
create_documentC
Create a new Word document with optional metadata.
Inputs: filename (required), title, author.
customize_footnote_styleC
Customize footnote numbering and formatting in a Word document.
Inputs: filename (required), numbering_format, start_number, font_name, +1 more.
delete_footnote_from_documentC
Delete a footnote from a Word document. Identify the footnote either by ID (1, 2, 3, etc.) or by searching for text near it.
Inputs: filename (required), footnote_id, search_text, output_filename.
delete_footnote_robustC
Delete footnote with comprehensive cleanup and orphan removal. Ensures complete removal from document.xml, footnotes.xml, and relationships.
Inputs: filename (required), footnote_id, search_text, clean_orphans.
delete_paragraphC
Delete a paragraph from a document.
Inputs: filename (required), paragraph_index (required).
find_text_in_documentC
Find occurrences of specific text in a Word document.
Inputs: filename (required), text_to_find (required), match_case, whole_word.
format_tableC
Format a table with borders, shading, and structure.
Inputs: filename (required), table_index (required), has_header_row, border_style, +1 more.
format_table_cell_textC
Format text within a specific table cell.
Inputs: filename (required), table_index (required), row_index (required), col_index (required), +7 more.
format_textC
Format a specific range of text within a paragraph.
Inputs: filename (required), paragraph_index (required), start_pos (required), end_pos (required), +6 more.
get_all_commentsC
Extract all comments from a Word document.
Inputs: filename (required).
get_comments_by_authorC
Extract comments from a specific author in a Word document.
Inputs: filename (required), author (required).
get_comments_for_paragraphC
Extract comments for a specific paragraph in a Word document.
Inputs: filename (required), paragraph_index (required).
get_document_infoC
Get information about a Word document.
Inputs: filename (required).
get_document_outlineC
Get the structure of a Word document.
Inputs: filename (required).
get_document_textC
Extract all text from a Word document.
Inputs: filename (required).
get_document_xmlC
Get the raw XML structure of a Word document.
Inputs: filename (required).
get_paragraph_text_from_documentC
Get text from a specific paragraph in a Word document.
Inputs: filename (required), paragraph_index (required).
highlight_table_headerC
Apply special highlighting to table header row.
Inputs: filename (required), table_index (required), header_color, text_color.
insert_header_near_textA
Insert a header (with specified style) before or after the target paragraph. Specify by text or paragraph index. Args: filename (str), target_text (str, optional), header_title (str), position ('before' or 'after'), header_style (str, default 'Heading 1'), target_paragraph_index (int, optional).
Inputs: filename (required), target_text, header_title, position, +2 more.
insert_line_or_paragraph_near_textB
Insert a new line or paragraph (with specified or matched style) before or after the target paragraph. Specify by text or paragraph index. Args: filename (str), target_text (str, optional), line_text (str), position ('before' or 'after'), line_style (str, optional), target_paragraph_index (int, optional).
Inputs: filename (required), target_text, line_text, position, +2 more.
insert_numbered_list_near_textA
Insert a bulleted or numbered list before or after the target paragraph. Specify by text or paragraph index. Args: filename (str), target_text (str, optional), list_items (list of str), position ('before' or 'after'), target_paragraph_index (int, optional), bullet_type ('bullet' for bullets or 'number' for numbered lists, default: 'bullet').
Inputs: filename (required), target_text, list_items, position, +2 more.
list_available_documentsC
List all .docx files in the specified directory.
Inputs: directory.
merge_table_cellsC
Merge cells in a rectangular area of a table.
Inputs: filename (required), table_index (required), start_row (required), start_col (required), +2 more.
merge_table_cells_horizontalC
Merge cells horizontally in a single row.
Inputs: filename (required), table_index (required), row_index (required), start_col (required), +1 more.
merge_table_cells_verticalC
Merge cells vertically in a single column.
Inputs: filename (required), table_index (required), col_index (required), start_row (required), +1 more.
protect_documentC
Add password protection to a Word document.
Inputs: filename (required), password (required).
replace_block_between_manual_anchorsC
Replace all content between start_anchor_text and end_anchor_text (or next logical header if not provided).
Inputs: filename (required), start_anchor_text (required), new_paragraphs (required), end_anchor_text, +2 more.
replace_paragraph_block_below_headerC
Reemplaza el bloque de párrafos debajo de un encabezado, evitando modificar TOC.
Inputs: filename (required), header_text (required), new_paragraphs (required), detect_block_end_fn.
search_and_replaceC
Search for text and replace all occurrences.
Inputs: filename (required), find_text (required), replace_text (required).
set_table_alignment_allC
Set text alignment for all cells in a table.
Inputs: filename (required), table_index (required), horizontal, vertical.
set_table_cell_alignmentC
Set text alignment for a specific table cell.
Inputs: filename (required), table_index (required), row_index (required), col_index (required), +2 more.
set_table_cell_paddingC
Set padding/margins for a specific table cell.
Inputs: filename (required), table_index (required), row_index (required), col_index (required), +5 more.
set_table_cell_shadingC
Apply shading/filling to a specific table cell.
Inputs: filename (required), table_index (required), row_index (required), col_index (required), +2 more.
set_table_column_widthC
Set the width of a specific table column.
Inputs: filename (required), table_index (required), col_index (required), width (required), +1 more.
set_table_column_widthsC
Set the widths of multiple table columns.
Inputs: filename (required), table_index (required), widths (required), width_type.
set_table_widthC
Set the overall width of a table.
Inputs: filename (required), table_index (required), width (required), width_type.
unprotect_documentC
Remove password protection from a Word document.
Inputs: filename (required), password (required).
validate_document_footnotesC
Validate all footnotes in document for coherence and compliance. Returns detailed report on ID conflicts, orphaned content, missing styles, etc.
Inputs: filename (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 54 tools
Multiple tools have overlapping purposes, especially for footnotes (e.g., add_footnote_to_document, add_footnote_enhanced, add_footnote_robust, add_footnote_before_text, add_footnote_after_text) and table formatting (e.g., set_table_cell_alignment vs. set_table_alignment_all, merge_table_cells vs. merge_table_cells_horizontal/vertical). Descriptions help somewhat, but the boundaries are unclear, leading to potential misselection.
The naming follows a mostly snake_case pattern, but conventions are mixed with inconsistent verb styles (e.g., 'add' vs. 'insert' vs. 'apply' vs. 'set' for similar operations) and some tools have overly verbose names (e.g., replace_block_between_manual_anchors). While readable, it lacks a predictable pattern across all tools.
With 54 tools, the count is excessive for a Word document server, making it heavy and overwhelming. Many tools could be consolidated (e.g., multiple footnote addition/deletion tools, redundant table formatting functions), indicating poor scoping and bloat.
The tool set covers a wide range of Word document operations, including creation, formatting, tables, footnotes, comments, and conversion to PDF. Minor gaps exist (e.g., no direct tool for adding comments or managing sections), but core workflows are well-covered, allowing agents to work around most limitations.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Related MCP Servers
- AlicenseAqualityDmaintenanceA server providing tools to read, write, and edit Microsoft Word (docx) files through the Model Context Protocol, allowing operations like complete document reading, content creation, targeted paragraph editing, and text insertion.439MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows Claude Desktop to perform document operations on Microsoft Word, Excel, and PDF files including creation, editing, and format conversion.52MIT
- FlicenseAqualityDmaintenanceA comprehensive Model Context Protocol server that processes Microsoft Word documents with full formatting support, enabling text extraction, HTML/Markdown conversion, structure analysis, and image extraction.52-
- -licenseNot gradedqualityNot gradedmaintenanceA Python server implementing Model Context Protocol for advanced Microsoft Word document manipulation, enabling programmatic automation of complex document processing tasks.-