Microsoft Word

A Model Context Protocol (MCP) server for creating, reading, and manipulating Microsoft Word documents. This server enables AI assistants to work with Word documents through a standardized interface, providing rich document editing capabilities.

Office-Word-MCP-Server implements theModel Context Protocolto expose Word document operations as tools and resources. It serves as a bridge between AI assistants and Microsoft Word documents, allowing for document creation, content addition, formatting, and analysis.

To install Office Word Document Server for Claude Desktop automatically viaSmithery:

npx -y @smithery/cli install @GongRzhe/Office-Word-MCP-Server --client claude

# 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

{ "mcpServers": { "word-document-server": { "command": "python", "args": ["/path/to/word_mcp_server.py"] } } }

Method 2: Without Installation (Using uvx)

{ "mcpServers": { "word-document-server": { "command": "uvx", "args": ["--from", "office-word-mcp-server", "word_mcp_server"] } } }

- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json

Restart Claude for Desktop to load the configuration.

Once configured, you can ask Claude to perform operations like:

- "Create a new document called 'report.docx' with a title page"
- "Add a heading and three paragraphs to my document"
- "Add my name in Helvetica 36pt bold at the top of the document"
- "Add a section heading 'Summary' in Helvetica 14pt bold with a bottom border"
- "Add a paragraph in Times New Roman 14pt with italic blue text"
- "Insert a bulleted list after the paragraph containing 'Introduction'"
- "Insert a numbered list with items: 'First step', 'Second step', 'Third step'"
- "Add bullet points after the 'Summary' heading"
- "Insert a 4x4 table with sales data"
- "Format the word 'important' in paragraph 2 to be bold and red"
- "Search and replace all instances of 'old term' with 'new term'"
- "Create a custom style for section headings"
- "Apply formatting to the table in my document"
- "Extract all comments from my document"
- "Show me all comments by John Doe"
- "Get comments for paragraph 3"
- "Make the text in table cell (1,2) bold and blue with 14pt font"
- "Add 10 points of padding to all sides of the header cells"
- "Create a callout table with a blue checkmark icon and white text"
- "Set the first column width to 50 points and auto-fit the remaining columns"
- "Apply alternating row colors to make the table more readable"

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)

add_heading(filename, text, level=1, font_name=None, font_size=None, bold=None, italic=None, border_bottom=False) add_paragraph(filename, text, style=None, font_name=None, font_size=None, bold=None, italic=None, color=None) add_table(filename, rows, cols, data=None) add_picture(filename, image_path, width=None) add_page_break(filename)

# Insert content relative to existing text or paragraph index insert_header_near_text(filename, target_text=None, header_title=None, position='after', header_style='Heading 1', target_paragraph_index=None) insert_line_or_paragraph_near_text(filename, target_text=None, line_text=None, position='after', line_style=None, target_paragraph_index=None) # Insert bulleted or numbered lists with proper XML formatting insert_numbered_list_near_text(filename, target_text=None, list_items=None, position='after', target_paragraph_index=None, bullet_type='bullet') # bullet_type options: # 'bullet' - Creates bulleted list with bullets (•) # 'number' - Creates numbered list (1, 2, 3, ...)

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)

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)

format_table(filename, table_index, has_header_row=None, border_style=None, shading=None) set_table_cell_shading(filename, table_index, row_index, col_index, fill_color, pattern="clear") apply_table_alternating_rows(filename, table_index, color1="FFFFFF", color2="F2F2F2") highlight_table_header(filename, table_index, header_color="4472C4", text_color="FFFFFF") # Cell merging tools merge_table_cells(filename, table_index, start_row, start_col, end_row, end_col) merge_table_cells_horizontal(filename, table_index, row_index, start_col, end_col) merge_table_cells_vertical(filename, table_index, col_index, start_row, end_row) # Cell alignment tools set_table_cell_alignment(filename, table_index, row_index, col_index, horizontal="left", vertical="top") set_table_alignment_all(filename, table_index, horizontal="left", vertical="top") # Cell text formatting tools format_table_cell_text(filename, table_index, row_index, col_index, text_content=None, bold=None, italic=None, underline=None, color=None, font_size=None, font_name=None) # Cell padding tools set_table_cell_padding(filename, table_index, row_index, col_index, top=None, bottom=None, left=None, right=None, unit="points") # Column width management set_table_column_width(filename, table_index, col_index, width, width_type="points") set_table_column_widths(filename, table_index, widths, width_type="points") set_table_width(filename, table_index, width, width_type="points") auto_fit_table_columns(filename, table_index)

get_all_comments(filename) get_comments_by_author(filename, author) get_comments_for_paragraph(filename, paragraph_index)

- Some documents may lack required styles for heading and table operations
- The server will attempt to create missing styles or use direct formatting
- For best results, use templates with standard Word styles

- Ensure the server has permission to read/write to the document paths
- Use thecopy_documentfunction to create editable copies of locked documents
- Check file ownership and permissions if operations fail

- Use absolute paths for image files
- Verify image format compatibility (JPEG, PNG recommended)
- Check image file size and permissions

- Cell index errors: Ensure row and column indices are within table bounds (0-based indexing)
- Color format problems: Use hex colors without '#' prefix (e.g., "FF0000" for red) or standard color names
- Padding unit confusion: Specify "points" or "percent" explicitly when setting cell padding
- Column width conflicts: Auto-fit may override manual column width settings
- Text formatting persistence: Apply cell text formatting after setting cell content for best results

Enable detailed logging by setting the environment variable:

export MCP_DEBUG=1 # Linux/macOS set MCP_DEBUG=1 # Windows

Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (git checkout -b feature/amazing-feature)
- Commit your changes (git commit -m 'Add some amazing feature')
- Push to the branch (git push origin feature/amazing-feature)
- Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

- Model Context Protocolfor the protocol specification
- python-docxfor Word document manipulation
- FastMCPfor the Python MCP implementation

An MCP server for reading and writing local XMind mind map files. Exposes over 25 tools that let any MCP-compatible AI client create, navigate, and edit .xmind files directly on disk.