MCP Documents
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Documents Convert the attached markdown to DOCX"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Documents
Unified MCP Server for Document Processing
A comprehensive Model Context Protocol (MCP) server that combines the best features from multiple document processing libraries into a single, efficient Python 3.10 compatible engine.
Features
π Word Document Operations (DOCX)
Create/Open/Save - Full document lifecycle management
Content - Paragraphs, headings, tables, images
Formatting - Font styles, colors, alignment, spacing
Tables - Create, edit, merge cells, add/delete rows
Sections - Page layout, margins, orientation
Headers/Footers - Add, modify, zone-based headers
Styles - Built-in and custom styles management
Search/Replace - Find and replace with preview
π Format Conversion
DOCX β PDF - Bidirectional conversion
Markdown β DOCX/PDF - With styling support
Markdown β PPTX - PowerPoint presentations
Image formats - PNG, JPG, WebP, GIF, BMP, TIFF
Excel β CSV - Spreadsheet conversion
HTML β PDF - Web page to document
π¨ Advanced Features
Template support - Reference documents for styling
Pandoc integration - Advanced format conversion
Base64 I/O - Direct content handling without files
Batch operations - Multiple edits in one call
Related MCP server: MCP-OPENAPI-DOCX
Installation
cd MCP-Documents
python3 -m venv .venv
source .venv/bin/activate
pip install -e .Optional Dependencies
For PDF conversion:
pip install -e ".[pdf]"For all features:
pip install -e ".[full]"External Tools
Some features require external tools:
Pandoc - For advanced format conversion:
sudo apt install pandocLibreOffice - For DOCXβPDF on Linux:
sudo apt install libreofficewkhtmltopdf - For HTMLβPDF:
sudo apt install wkhtmltopdf
Configuration
Claude Desktop / VS Code
Add to your MCP configuration:
{
"mcpServers": {
"mcp-documents": {
"command": "/path/to/MCP-Documents/.venv/bin/python",
"args": ["-m", "mcp_documents.server"]
}
}
}Usage Examples
Create a Document
"Create a new Word document called report.docx with title 'Q4 Report'"Add Content
"Add a heading 'Summary' at level 2, then add a paragraph with the quarterly results"Format Text
"Make the title bold and center-aligned, set font size to 24pt"Add Tables
"Insert a 3x4 table with sales data, merge the header row"Convert Formats
"Convert report.docx to PDF"
"Convert this markdown to PowerPoint and save as presentation.pptx"Available Tools
Document Management
Tool | Description |
| Create new Word document |
| Open existing document |
| Save current document |
| Save as new file |
| Get document statistics |
Content Operations
Tool | Description |
| Add paragraph with formatting |
| Add heading (level 1-9) |
| Create table with data |
| Insert image |
| Insert page break |
Table Operations
Tool | Description |
| Modify cell content |
| Add row to table |
| Remove row |
| Merge cell range |
Format Conversion
Tool | Description |
| DOCX β PDF |
| PDF β DOCX |
| MD β DOCX/PDF/PPTX |
| Image format conversion |
Search & Edit
Tool | Description |
| Find text in document |
| Replace text |
| Remove paragraph |
Architecture
mcp_documents/
βββ __init__.py # Package exports
βββ server.py # MCP server entry point
βββ core/
β βββ document.py # Document processor class
β βββ formatting.py # Text/paragraph formatting
β βββ utils.py # Helper functions
βββ tools/
β βββ document_ops.py # Document CRUD operations
β βββ content_ops.py # Content manipulation
β βββ table_ops.py # Table operations
β βββ style_ops.py # Style management
β βββ section_ops.py # Section/layout operations
β βββ header_footer.py # Headers and footers
β βββ conversion.py # Format conversion tools
βββ converters/
βββ pdf.py # PDF conversion
βββ image.py # Image conversion
βββ pandoc.py # Pandoc wrapperLicense
MIT License
Available Tools
133 toolsaccept_all_changesA
Accept all tracked changes in the document. Insertions are kept, deletions are removed.
Inputs: no named parameters. Returns: result
add_bookmarkA
Add a bookmark to a paragraph in the document. Bookmarks can be used for internal navigation.
Args: paragraph_index: Index of the paragraph to bookmark bookmark_name: Name for the bookmark (no spaces)
Returns: Success or error message
Inputs: bookmark_name (required), paragraph_index (required). Returns: result
add_bulleted_listB
Add a bulleted list to the document.
Args: items: List of item texts style: List style - "List Bullet", "List Bullet 2", "List Bullet 3"
Returns: Success message or error
Inputs: items (required), style. Returns: result
add_commentB
Add a comment to a paragraph.
Args: comment_text: The comment text paragraph_index: Index of paragraph to comment on (0-based) author: Comment author name initials: Author initials
Returns: Success message or error
Inputs: comment_text (required), paragraph_index (required), author, initials. Returns: result
add_endnoteB
Add an endnote to a specific paragraph. Endnotes appear at the end of the document.
Args: paragraph_index: Index of the paragraph to add endnote to endnote_text: Text content of the endnote
Returns: Success or error message
Inputs: endnote_text (required), paragraph_index (required). Returns: result
add_footnoteC
Add a footnote to a paragraph.
Inputs: text (required), paragraph_index (required). Returns: result
add_headerA
Add a header to the document section.
Args: text: Header text content section_index: Section to add header to (default: 0) alignment: Text alignment - "left", "center", "right"
Returns: Success message or error
Inputs: text (required), alignment, section_index. Returns: result
add_headingB
Add a heading to the current document.
Args: text: Heading text level: Heading level (0-9, where 0 is Title)
Returns: Success message or error
Inputs: text (required), level. Returns: result
add_hyperlinkC
Add a hyperlink to a paragraph.
Inputs: url (required), text (required), paragraph_index (required), position. Returns: result
add_hyperlink_to_bookmarkA
Add a hyperlink that navigates to a bookmark in the document.
Args: text: Display text for the hyperlink bookmark_name: Name of the target bookmark
Returns: Success or error message
Inputs: text (required), bookmark_name (required). Returns: result
add_imageB
Add an image to the current document.
Args: image_path: Path to the image file width_inches: Optional width in inches height_inches: Optional height in inches
Returns: Success message or error
Inputs: image_path (required), width_inches, height_inches. Returns: result
add_image_base64B
Add an image from base64 encoded data.
Args: base64_data: Base64 encoded image (with or without data URI prefix) width_inches: Optional width in inches
Returns: Success or error message
Inputs: base64_data (required), width_inches. Returns: result
add_list_itemC
Add a single list item.
Args: text: Item text list_type: "bullet" or "number"
Returns: Success message or error
Inputs: text (required), list_type. Returns: result
add_merge_fieldB
Add a mail merge field to the document. The field will be replaced with actual data during mail merge.
Args: field_name: Name of the merge field (e.g., 'FirstName', 'Address')
Returns: Success or error message
Inputs: field_name (required). Returns: result
add_multilevel_listA
Add a multi-level list with nested items.
Args: items: List of dicts with 'text' and 'level' keys Example: [{"text": "Item 1", "level": 0}, {"text": "Sub item", "level": 1}]
Returns: Success message or error
Inputs: items (required). Returns: result
add_native_footnoteB
Add a native Word footnote to a specific paragraph.
Args: paragraph_index: Index of the paragraph to add footnote to footnote_text: Text content of the footnote
Returns: Success or error message
Inputs: footnote_text (required), paragraph_index (required). Returns: result
add_numbered_listA
Add a numbered list to the document.
Args: items: List of item texts style: List style - "List Number", "List Number 2", "List Number 3"
Returns: Success message or error
Inputs: items (required), style. Returns: result
add_page_breakA
Add a page break to the current document.
Returns: Success message or error
Inputs: no named parameters. Returns: result
add_page_numbersA
Add page numbers to header or footer.
Args: position: "header" or "footer" alignment: "left", "center", or "right" format_string: Format - use {page} for page number section_index: Section to add to
Returns: Success message or error
Inputs: position, alignment, format_string, section_index. Returns: result
add_paragraphA
Add a paragraph to the current document.
Args: text: Paragraph text content style: Optional Word style name (e.g., "Normal", "Quote") bold: Make text bold italic: Make text italic underline: Underline text font_size: Font size in points font_name: Font name (e.g., "Arial", "Times New Roman") color: Text color as hex (e.g., "#FF0000") or name (e.g., "red") alignment: Text alignment ("left", "center", "right", "justify")
Returns: Success message or error
Inputs: text (required), bold, color, style, +5 more. Returns: result
add_sectionA
Add a new section to the document.
Returns: Success message with section count
Inputs: no named parameters. Returns: result
add_section_breakB
Add a new section break to the document.
Args: section_type: Type of section break: - 'NEW_PAGE': Start on new page (default) - 'CONTINUOUS': Continue on same page - 'ODD_PAGE': Start on next odd page - 'EVEN_PAGE': Start on next even page
Returns: Success or error message
Inputs: section_type. Returns: result
add_tableA
Add a table to the current document.
Args: rows: Number of rows cols: Number of columns data: Optional 2D array of cell data style: Table style name (default: "Table Grid")
Returns: Success message or error
Inputs: cols (required), rows (required), data, style. Returns: result
add_table_of_contentsC
Add a Table of Contents to the document. The TOC will include headings up to the specified level.
Args: title: Title for the TOC section heading_levels: Number of heading levels to include (1-9)
Returns: Success or error message
Note: Open the document in Word and update the field to populate the TOC.
Inputs: title, heading_levels. Returns: result
add_table_rowB
Add a row to an existing table.
Args: table_index: Table index (0-based) data: Optional list of cell values
Returns: Success message or error
Inputs: table_index (required), data. Returns: result
add_text_watermarkC
Add a simple text watermark via header.
Inputs: text, section_index. Returns: result
add_zoned_headerC
Add a header with left, center, and right zones.
Args: section_index: Section to add header to left_text: Text for left zone center_text: Text for center zone right_text: Text for right zone
Returns: Success or error message
Inputs: left_text, right_text, center_text, section_index. Returns: result
append_table_rowC
Append a row to a table.
Args: table_index: Index of the table data: Optional list of cell values for the new row
Returns: Success or error message
Inputs: table_index (required), data. Returns: result
apply_table_alternating_rowsC
Apply alternating row colors to a table.
Inputs: table_index (required), color1, color2. Returns: result
batch_format_paragraphsA
Apply a style to a range of paragraphs.
Args: style_name: Name of the style to apply (e.g., 'Normal', 'Heading 1') start_index: Starting paragraph index (default 0) end_index: Ending paragraph index (exclusive, default all remaining)
Returns: Success message with count or error message
Inputs: style_name (required), end_index, start_index. Returns: result
batch_replaceB
Replace multiple strings in the document at once.
Args: replacements: Dictionary of old -> new text replacements Example: {"old1": "new1", "old2": "new2"}
Returns: Success message with replacement count or error message
Inputs: replacements (required). Returns: result
check_pandocA
Check if Pandoc is available and get supported formats.
Returns: Pandoc status and supported formats
Inputs: no named parameters. Returns: result
close_documentA
Close the current document without saving.
Returns: Success message
Inputs: no named parameters. Returns: result
convert_documentA
Convert between document formats using Pandoc.
Args: input_path: Path to input file output_path: Path for output file from_format: Optional input format (auto-detected if not specified) to_format: Optional output format (auto-detected if not specified)
Returns: Output path or error message
Supported formats: markdown, docx, html, latex, epub, odt, rtf, and more.
Inputs: input_path (required), output_path (required), to_format, from_format. Returns: result
convert_docx_to_markdownA
Convert Word document to Markdown.
Args: input_path: Path to input DOCX file output_path: Optional output Markdown path extract_media: Extract embedded images
Returns: Output path or error message
Inputs: input_path (required), output_path, extract_media. Returns: result
convert_docx_to_pdfA
Convert a Word document to PDF.
Args: input_path: Path to input DOCX file output_path: Optional output PDF path (auto-generated if not provided)
Returns: Output path or error message
Inputs: input_path (required), output_path. Returns: result
convert_html_to_docxA
Convert HTML to Word document.
Args: input_path: Path to input HTML file output_path: Optional output DOCX path reference_doc: Optional reference DOCX for styling
Returns: Output path or error message
Inputs: input_path (required), output_path, reference_doc. Returns: result
convert_html_to_pdfB
Convert HTML to PDF.
Args: input_path: Path to input HTML file output_path: Optional output PDF path (auto-generated if not provided)
Returns: Output path or error message
Inputs: input_path (required), output_path. Returns: result
convert_image_formatA
Convert an image to a different format with optional resizing.
Args: input_path: Path to input image output_path: Path for output image (format determined by extension) width: Optional new width in pixels height: Optional new height in pixels quality: JPEG quality (1-100)
Returns: Output path or error message
Inputs: input_path (required), output_path (required), width, height, +1 more. Returns: result
convert_markdown_to_docxA
Convert Markdown to Word document.
Args: input_path: Path to input Markdown file output_path: Optional output DOCX path reference_doc: Optional reference DOCX for styling
Returns: Output path or error message
Inputs: input_path (required), output_path, reference_doc. Returns: result
convert_markdown_to_htmlB
Convert Markdown to HTML.
Args: input_path: Path to input Markdown file output_path: Optional output HTML path css: Optional CSS file to include
Returns: Output path or error message
Inputs: input_path (required), css, output_path. Returns: result
convert_markdown_to_pptxB
Convert Markdown to PowerPoint presentation.
Args: input_path: Path to input Markdown file output_path: Optional output PPTX path reference_doc: Optional reference PPTX for styling
Returns: Output path or error message
Inputs: input_path (required), output_path, reference_doc. Returns: result
convert_pdf_to_docxB
Convert a PDF to Word document.
Args: input_path: Path to input PDF file output_path: Optional output DOCX path (auto-generated if not provided)
Returns: Output path or error message
Inputs: input_path (required), output_path. Returns: result
convert_with_pandoc_advancedB
Advanced Pandoc conversion with filters, defaults, metadata, variables, and custom PDF engine.
Args: input_path: Input file path output_path: Output file path from_format: Pandoc input format (optional, auto-detect by extension) to_format: Pandoc output format (optional, auto-detect by extension) filters: List of Pandoc filters to apply defaults_file: Path to defaults YAML file metadata: Metadata key/value pairs (--metadata key=value) variables: Template variables (--variable key=value) reference_doc: Reference docx/pptx for styling template: Pandoc template path pdf_engine: PDF engine (e.g., xelatex) extra_args: Additional Pandoc args standalone: Produce standalone document
Returns: Output path or error message
Inputs: input_path (required), output_path (required), filters, metadata, +9 more. Returns: result
copy_documentC
Create a copy of the current document.
Args: dest_path: Destination file path
Returns: Success or error message
Inputs: dest_path (required). Returns: result
count_paragraphsA
Get the number of paragraphs in the current document.
Returns: Paragraph count or error
Inputs: no named parameters. Returns: result
create_documentB
Create a new Word document.
Args: file_path: Full path where to save the document title: Optional title to add as heading
Returns: Success message or error
Inputs: file_path (required), title. Returns: result
csv_to_excelA
Convert a CSV file to Excel format. Requires openpyxl package.
Args: csv_path: Path to the CSV file excel_path: Path for the output Excel file (.xlsx) sheet_name: Name for the sheet
Returns: Success or error message
Inputs: csv_path (required), excel_path (required), sheet_name. Returns: result
csv_to_tableA
Import a CSV file as a table in the current document.
Args: csv_path: Path to the CSV file delimiter: Column delimiter (default comma)
Returns: Success or error message
Inputs: csv_path (required), delimiter. Returns: result
delete_all_commentsA
Delete all comments from the document.
Returns: Success message or error
Inputs: no named parameters. Returns: result
delete_paragraphB
Delete a paragraph by index.
Args: index: Paragraph index (0-based)
Returns: Success message or error
Inputs: index (required). Returns: result
delete_table_rowA
Delete a row from a table.
Args: table_index: Table index (0-based) row_index: Row index to delete (0-based)
Returns: Success message or error
Inputs: row_index (required), table_index (required). Returns: result
disable_track_changesA
Disable track changes in the current document. Future edits will not be tracked.
Inputs: no named parameters. Returns: result
edit_table_cellA
Edit the content of a table cell.
Args: table_index: Table index (0-based) row_index: Row index (0-based) col_index: Column index (0-based) text: New cell text
Returns: Success message or error
Inputs: text (required), col_index (required), row_index (required), table_index (required). Returns: result
enable_track_changesA
Enable track changes in the current document. All subsequent edits will be tracked as revisions.
Inputs: no named parameters. Returns: result
excel_to_csvA
Convert an Excel file to CSV format. Requires openpyxl package.
Args: excel_path: Path to the Excel file (.xlsx) csv_path: Path for the output CSV file sheet_name: Name of the sheet to convert (default: active sheet)
Returns: Success or error message
Inputs: csv_path (required), excel_path (required), sheet_name. Returns: result
excel_to_tableA
Import an Excel file as a table in the current document. Requires openpyxl package.
Args: excel_path: Path to the Excel file (.xlsx) sheet_name: Name of the sheet to import (default: active sheet) max_rows: Maximum rows to import (default 100)
Returns: Success or error message
Inputs: excel_path (required), max_rows, sheet_name. Returns: result
execute_mail_mergeB
Execute mail merge with provided data. Creates one document per record.
Args: data: List of dictionaries with field values Example: [{"FirstName": "John", "LastName": "Doe"}, ...] output_pattern: Output filename pattern with {index} placeholder Example: "letter_{index}.docx"
Returns: Success message with list of created files or error message
Inputs: data (required), output_pattern (required). Returns: result
find_and_replaceC
Find and replace text in the current document.
Args: find_text: Text to find replace_text: Text to replace with
Returns: Number of replacements made
Inputs: find_text (required), replace_text (required). Returns: result
find_textC
Find all occurrences of text in the document.
Args: search_text: Text to search for case_sensitive: Whether to match case
Returns: List of occurrences or error message
Inputs: search_text (required), case_sensitive. Returns: result
get_all_commentsB
Get all comments from the document.
Returns: List of all comments with metadata
Inputs: no named parameters. Returns: result
get_comment_countA
Get the number of comments in the document.
Returns: Comment count
Inputs: no named parameters. Returns: result
get_comments_by_authorC
Get comments filtered by author name.
Args: author: Author name to filter by
Returns: List of comments by the specified author
Inputs: author (required). Returns: result
get_document_infoB
Get information about the current document.
Returns: Document information including sections, paragraphs, tables count
Inputs: no named parameters. Returns: result
get_document_outlineA
Get the document outline based on headings. Returns a hierarchical view of all headings.
Returns: Document outline or error message
Inputs: no named parameters. Returns: result
get_document_statisticsB
Get comprehensive statistics about the document. Includes paragraph count, word count, table count, etc.
Returns: Document statistics or error message
Inputs: no named parameters. Returns: result
get_document_structureA
Get structural overview of the document. Includes sections, paragraphs, tables, and heading outline.
Returns: Document structure or error message
Inputs: no named parameters. Returns: result
get_document_textB
Get all text content from the current document.
Returns: All paragraph text from the document
Inputs: no named parameters. Returns: result
get_formatting_reportA
Get a report of fonts and styles used in the document. Useful for checking formatting consistency.
Returns: Formatting report or error message
Inputs: no named parameters. Returns: result
get_header_textC
Get the header text from a section.
Args: section_index: Section to get header from
Returns: Header text or error
Inputs: section_index. Returns: result
get_image_as_base64A
Convert an image file to base64 string with data URI prefix.
Args: image_path: Path to the image file
Returns: Base64 data URI string or error message
Inputs: image_path (required). Returns: result
get_image_detailsA
Get information about an image file.
Args: image_path: Path to the image file
Returns: Image information (format, size, dimensions)
Inputs: image_path (required). Returns: result
get_metadataA
Get document metadata/properties. Includes title, author, subject, keywords, dates, etc.
Returns: Document metadata or error message
Inputs: no named parameters. Returns: result
get_page_infoA
Get page layout information.
Args: section_index: Section to query (default: 0)
Returns: Page size, margins, and orientation
Inputs: section_index. Returns: result
get_paragraphB
Get text of a specific paragraph.
Args: index: Paragraph index (0-based)
Returns: Paragraph text or error
Inputs: index (required). Returns: result
get_paragraph_textA
Get text from a specific paragraph.
Args: index: Paragraph index (0-based)
Returns: Paragraph text or error message
Inputs: index (required). Returns: result
get_raw_xmlA
Get the raw XML structure of the document body. Useful for debugging and advanced manipulation.
Returns: XML string (may be truncated) or error message
Inputs: no named parameters. Returns: result
get_table_contentC
Get all content from a specific table.
Args: table_index: Table index (0-based)
Returns: Table content as formatted text or error
Inputs: table_index (required). Returns: result
get_table_dataB
Get all data from a table as text.
Args: table_index: Index of the table
Returns: Table data or error message
Inputs: table_index (required). Returns: result
get_tables_infoB
Get information about all tables in the document.
Returns: Table information including dimensions
Inputs: no named parameters. Returns: result
get_word_countA
Get detailed word count statistics. Includes words, characters, paragraphs, and lines.
Returns: Word count statistics or error message
Inputs: no named parameters. Returns: result
highlight_table_headerC
Highlight the first row as header.
Inputs: table_index (required), text_color, header_color. Returns: result
insert_documentC
Insert a single document at the end of current document.
Inputs: file_path (required). Returns: result
insert_imageC
Insert an image into the document.
Args: image_path: Path to the image file width_inches: Optional width in inches height_inches: Optional height in inches
Returns: Success or error message
Inputs: image_path (required), width_inches, height_inches. Returns: result
insert_paragraph_afterA
Insert a paragraph after the specified index.
Args: index: Paragraph index to insert after text: Text content for new paragraph style: Optional style name
Returns: Success or error message
Inputs: text (required), index (required), style. Returns: result
list_bookmarksA
List all bookmarks in the current document.
Returns: Comma-separated list of bookmark names or error message
Inputs: no named parameters. Returns: result
list_docx_filesA
List all .docx files in a directory.
Args: directory: Path to directory to scan
Returns: List of files or error message
Inputs: directory (required). Returns: result
list_imagesA
List all images in the document with dimensions.
Returns: List of images or error message
Inputs: no named parameters. Returns: result
list_open_documentsA
List all currently open documents.
Returns: List of open document paths
Inputs: no named parameters. Returns: result
list_sectionsA
List all sections in the document with their properties. Shows orientation, page size, and margins for each section.
Returns: Section listing or error message
Inputs: no named parameters. Returns: result
list_stylesA
List available paragraph styles in the document.
Returns: List of style names
Inputs: no named parameters. Returns: result
list_tablesA
List all tables with their dimensions and styles.
Returns: Table listing or error message
Inputs: no named parameters. Returns: result
merge_cellsC
Merge cells in a rectangular area.
Args: table_index: Index of the table start_row: Starting row start_col: Starting column end_row: Ending row end_col: Ending column
Returns: Success or error message
Inputs: end_col (required), end_row (required), start_col (required), start_row (required), +1 more. Returns: result
merge_documentsC
Merge multiple documents into the current document.
Inputs: file_paths (required). Returns: result
merge_table_cellsC
Merge multiple table cells.
Args: table_index: Table index (0-based) start_row: Starting row index start_col: Starting column index end_row: Ending row index end_col: Ending column index
Returns: Success message or error
Inputs: end_col (required), end_row (required), start_col (required), start_row (required), +1 more. Returns: result
open_documentB
Open an existing Word document for editing.
Args: file_path: Full path to the document
Returns: Success message or error
Inputs: file_path (required). Returns: result
protect_documentA
Protect the document with specified restrictions.
Args: protection_type: Type of protection: - 'readOnly': Document is read-only - 'comments': Only comments allowed - 'trackedChanges': Only tracked changes allowed - 'forms': Only form fields can be edited password: Optional password to protect the document
Returns: Success or error message
Inputs: password, protection_type. Returns: result
read_csvA
Read a CSV file and return its contents.
Args: file_path: Path to the CSV file delimiter: Column delimiter (default comma) has_header: Whether the first row is a header
Returns: CSV contents as formatted text or error message
Inputs: file_path (required), delimiter, has_header. Returns: result
read_excelA
Read an Excel file and return its contents. Requires openpyxl package.
Args: file_path: Path to the Excel file (.xlsx) sheet_name: Name of the sheet to read (default: active sheet)
Returns: Excel contents as formatted text or error message
Inputs: file_path (required), sheet_name. Returns: result
redact_textA
Redact text matching pattern throughout the document.
Args: pattern: Text or regex pattern to find replacement: Replacement text (default: [REDACTED]) use_regex: Whether to use regex matching
Returns: Count of redactions or error message
Inputs: pattern (required), use_regex, replacement. Returns: result
reject_all_changesA
Reject all tracked changes in the document. Insertions are removed, deletions are restored.
Inputs: no named parameters. Returns: result
remove_headerC
Remove header from a section.
Args: section_index: Section to remove header from
Returns: Success message or error
Inputs: section_index. Returns: result
remove_paragraphB
Remove a paragraph by index.
Args: index: Paragraph index (0-based)
Returns: Success or error message
Inputs: index (required). Returns: result
remove_table_rowC
Remove a row from a table.
Args: table_index: Index of the table row_index: Index of the row to remove
Returns: Success or error message
Inputs: row_index (required), table_index (required). Returns: result
render_endnotesA
Render all endnotes at the end of the document. Creates an 'Endnotes' section with numbered entries.
Returns: Success or error message
Inputs: no named parameters. Returns: result
sanitize_external_linksB
Remove all external hyperlinks from the document. Link text is preserved but the hyperlink is removed.
Returns: Count of removed links or error message
Inputs: no named parameters. Returns: result
save_base64_as_imageA
Save a base64 encoded image to a file.
Args: base64_data: Base64 encoded image data (with or without data URI prefix) output_path: Path for output image file
Returns: Output path or error message
Inputs: base64_data (required), output_path (required). Returns: result
save_documentA
Save the current document.
Args: file_path: Optional new path to save as (uses current path if not specified)
Returns: Success message or error
Inputs: file_path. Returns: result
search_textB
Search for text in the current document.
Args: keyword: Text to search for
Returns: Search results with locations
Inputs: keyword (required). Returns: result
set_cell_alignmentC
Set horizontal and vertical alignment for a cell.
Inputs: col_index (required), row_index (required), table_index (required), vertical, +1 more. Returns: result
set_cell_paddingC
Set padding for a cell (all sides).
Inputs: col_index (required), row_index (required), table_index (required), padding_cm. Returns: result
set_column_widthC
Set width for a specific column across all rows.
Inputs: width_cm (required), col_index (required), table_index (required). Returns: result
set_different_first_page_headerA
Set different header for first page vs other pages.
Args: first_page_text: Header text for first page other_pages_text: Header text for other pages section_index: Section to apply to
Returns: Success message or error
Inputs: first_page_text (required), other_pages_text (required), section_index. Returns: result
set_metadataC
Set document metadata/properties.
Args: title: Document title author: Document author subject: Document subject keywords: Keywords (comma-separated) category: Document category comments: Document comments
Returns: Success or error message
Inputs: title, author, subject, category, +2 more. Returns: result
set_page_marginsB
Set page margins for the document.
Args: top: Top margin in centimeters bottom: Bottom margin in centimeters left: Left margin in centimeters right: Right margin in centimeters section_index: Section to apply to (default: 0)
Returns: Success message or error
Inputs: top, left, right, bottom, +1 more. Returns: result
set_page_orientationB
Set page orientation.
Args: orientation: "portrait" or "landscape" section_index: Section to apply to (default: 0)
Returns: Success message or error
Inputs: orientation (required), section_index. Returns: result
set_page_sizeA
Set page size for the document.
Args: width: Page width in centimeters height: Page height in centimeters section_index: Section to apply to (default: 0)
Returns: Success message or error
Inputs: width (required), height (required), section_index. Returns: result
set_paragraph_textA
Replace text of a specific paragraph.
Args: index: Paragraph index (0-based) text: New text content
Returns: Success or error message
Inputs: text (required), index (required). Returns: result
set_row_heightA
Set the height of a specific row in a table.
Args: table_index: Index of the table row_index: Index of the row to modify height_cm: Height in centimeters rule: Height rule: - 'exact': Exact height - 'atLeast': Minimum height - 'auto': Automatic height
Returns: Success or error message
Inputs: height_cm (required), row_index (required), table_index (required), rule. Returns: result
set_section_propertiesB
Set properties for a specific section.
Args: section_index: Index of the section to modify orientation: 'PORTRAIT' or 'LANDSCAPE' width_inches: Page width in inches height_inches: Page height in inches top_margin: Top margin in inches bottom_margin: Bottom margin in inches left_margin: Left margin in inches right_margin: Right margin in inches
Returns: Success or error message
Inputs: top_margin, left_margin, orientation, right_margin, +4 more. Returns: result
set_table_bordersA
Set borders for a table with per-side control.
Args: table_index: Index of the table to modify top: Top border style bottom: Bottom border style left: Left border style right: Right border style inside_h: Inside horizontal border style inside_v: Inside vertical border style size: Border thickness (default 4) color: Border color as hex without # (default "000000")
Border styles: 'single', 'double', 'dotted', 'dashed', 'none'
Returns: Success or error message
Inputs: table_index (required), top, left, size, +5 more. Returns: result
set_table_cell_shadingC
Apply background color to a cell.
Inputs: col_index (required), row_index (required), table_index (required), fill_color. Returns: result
set_table_cell_textC
Set text in a specific table cell.
Args: table_index: Index of the table row: Row index col: Column index text: Text to set
Returns: Success or error message
Inputs: col (required), row (required), text (required), table_index (required). Returns: result
strip_personal_infoA
Remove personal information from document metadata. Clears author, last modified by, and comments.
Returns: Success or error message
Inputs: no named parameters. Returns: result
switch_documentC
Switch to a different open document.
Args: file_path: Path to the document to switch to
Returns: Success message or error
Inputs: file_path (required). Returns: result
table_to_csvA
Export a table from the document to a CSV file.
Args: table_index: Index of the table to export output_path: Path for the output CSV file delimiter: Column delimiter (default comma)
Returns: Success or error message
Inputs: output_path (required), table_index (required), delimiter. Returns: result
unprotect_documentA
Remove protection from the current document.
Returns: Success or error message
Inputs: no named parameters. Returns: result
update_tocA
Get instructions for updating the Table of Contents. TOC must be updated in Microsoft Word or compatible application.
Returns: Instructions for updating TOC
Inputs: no named parameters. Returns: result
write_csvB
Write data to a CSV file.
Args: file_path: Path for the output CSV file data: List of rows, each row is a list of values delimiter: Column delimiter (default comma)
Returns: Success or error message
Inputs: data (required), file_path (required), delimiter. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 133 tools
Many tools have overlapping purposes, such as multiple ways to add footnotes (add_footnote, add_native_footnote, add_endnote), insert images (add_image, add_image_base64, insert_image), and manipulate tables (add_table_row, append_table_row, delete_table_row, remove_table_row). Duplicate functions like delete_paragraph and remove_paragraph further confuse selection.
Tool names mostly follow verb_noun pattern, but inconsistencies exist: 'delete' vs 'remove', 'set' vs 'edit' vs 'update', and noun_to_noun patterns like csv_to_excel. Mixed naming conventions reduce predictability.
With 133 tools, the server is overloaded. While covering many operations, the count is excessive and likely to overwhelm agents, causing slower decision-making and higher chance of misselection.
The tool set is very comprehensive, covering document creation, editing, formatting, tables, images, comments, metadata, protection, mail merge, and conversions. Minor gaps exist, such as no tool to remove footnotes or manage styles in detail, but overall it covers most use cases.
Maintenance
Related MCP Connectors
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Document-to-Markdown MCP server β convert PDF, Office and HTML into LLM-ready Markdown.
Document processing over MCP: merge, split and compress PDFs, run OCR, extract document text.
Generate PDF, Word (.docx) and PowerPoint (.pptx) documents from Markdown over MCP.
Related MCP Servers
- AlicenseBqualityDmaintenanceA universal MCP server for document processing, conversion, and automation. Handle PDF, DOCX, HTML, Markdown, and more through a unified API and toolset.1318 npm140MIT
- AlicenseNot gradedqualityDmaintenanceEnterprise-grade document editing and management server that enables AI-powered operations on Microsoft Word DOCX files, including creating, editing, formatting, and exporting documents through both MCP protocol and RESTful API.3MIT
- AlicenseNot gradedqualityDmaintenanceA powerful Word document editing MCP server that provides complete document manipulation capabilities, including creation, editing, formatting, tables, images, and advanced features like footnotes and interface document generation.3MIT
- AlicenseAqualityDmaintenanceMCP server for Word document (.docx) creation and manipulation β the production-grade document automation tool for AI agents.946 npmMIT