Aspose.Words MCP
OfficialThis MCP server lets you create, edit, inspect, protect, sign, and export Word documents through tool calls.
Create, copy, list, merge, save, delete, and inspect documents, including text, XML, stats, outline, and base64 content.
Insert, read, replace, find, and delete text/paragraphs; add headings, custom styles, HTML, Markdown, images, lists, bookmarks, and hyperlinks.
Format text and create/format tables with rows, columns, widths, alignment, merging, shading, padding, header styling, and cell text formatting.
Manage layout with page/section breaks, page setup, columns, headers/footers, page numbering, and different first-page headers/footers.
Work with comments, footnotes, and endnotes, including anchor-based add/delete/validate operations and footnote-to-endnote conversion.
Read/write document properties, protect/unprotect/restrict editing, sign documents, and inspect digital signatures.
Add text and image watermarks.
Export to DOCX/PDF/etc. as base64, use advanced export options, render pages to images, and retrieve document binary content.
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., "@Aspose.Words MCP Create a document with heading and two paragraphs, then export as PDF."
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.
Aspose.Words MCP
Overview
Aspose.Words MCP is a FastMCP-based MCP server built on top of Aspose.Words for Python via .NET. It automates Microsoft Word document creation and editing and exposes operations as MCP tools that any MCP-compatible client can call. The server is aligned with Aspose.Words for Python via .NET 26.10.0. Supported transports: stdio, streamable-http, sse.
Related MCP server: MCP-OPENAPI-DOCX
Features
Create documents; read/write text, headings, and paragraphs
Text replacement workflows, including optional run joining when needed
Text formatting (font, size, style, color, underline)
Page and section breaks; page setup (margins, orientation, paper size, columns)
Lists (bulleted/numbered)
Tables: create, auto-fit, merge cells, alignment, shading, paddings, column widths, header styling
Charts: create column and waterfall charts, list charts, format plot-area fills and lines, inspect waterfall totals
Footnotes and endnotes: add, convert, anchor-based operations, validation
Comments: get by author, by paragraph, all comments
Document properties: read/write (title, author, subject, keywords)
Document comparison with revision output
Protection: protect/unprotect, partial editing restrictions
Digital signatures: sign documents with optional timestamp settings and inspect signature metadata
Bookmarks, hyperlinks
Watermarks (text/image)
Export as Base64 (DOCX, signed PDF, XPS, etc.)
Render page to image (PNG, etc.)
In-memory document management: copy, save as, list, delete, merge
Requirements
Python 3.11+
Aspose.Words for Python via .Net. This library is a commercial product.
You'll need to obtain a valid license for Aspose.Words. The package will install this dependency, but you're responsible for complying with Aspose's licensing terms.
Installation
pip install aspose-words-mcpFrom source (download repo and install requirements):
git clone https://github.com/aspose-words/Aspose.Words-MCP
cd Aspose.Words-MCP
pip install -r requirements.txtCommand Line Interface
After installation, the CLI command is available:
aspose-words-mcpBy default, the server runs with the stdio transport.
Run without installation:
python mcp_server.pyTransports and Configuration
Supported MCP transports: stdio, streamable-http, sse.
Environment Variables
MCP_TRANSPORT—stdio|streamable-http|sse(defaultstdio)MCP_HOST— host address (default0.0.0.0)MCP_PORT— port (default8080)MCP_PATH— HTTP path forstreamable-http(default/mcp)MCP_SSE_PATH— events path forsse(default/sse)LOG_LEVEL— logging level (INFO,DEBUG, ...)
Aspose.Words License
The Aspose.Words license is applied when the server starts. The effective path to the license file is resolved with the following precedence:
The
license_pathargument ofrun_server(..., license_path=None)The
ASPOSE_WORDS_LICENSE_PATHenvironment variable
If no license is provided or the file is not accessible, the server runs in Evaluation mode.
Example of setting the environment variable:
export ASPOSE_WORDS_LICENSE_PATH='/path/to/aspose.words.lic'HTTP/SSE Run Example
export MCP_TRANSPORT=streamable-http # or sse
export MCP_HOST=0.0.0.0
export MCP_PORT=8080
export MCP_PATH=/mcp # for streamable-http
export MCP_SSE_PATH=/sse # for sse
aspose-words-mcpOn start, the server prints the listening address.
Development Validation
Install development dependencies with python -m pip install -e '.[dev]', then run:
python -m pytest -q
python -m ruff check .
python -m ruff format . --check
python -m pyright --pythonpath .venv/bin/pythonAll four checks are required before merging a server update.
Tools
See full list and signatures in mcp_server.py (function register_tools) and tests in tests/features/*.
Main tool categories:
content/reading: create document, insert/delete/read text, headings, lists, HTML/Markdown
layout: pages, breaks, columns, headers/footers, page numbering
tables: create and format tables
charts:
add_chart_end,list_charts,format_chart_plot_area,get_waterfall_totalswatermarks: watermarks
links/bookmarks: hyperlinks and bookmarks
properties: document properties
comparison: compare documents and save revisions
protection: protection and restrictions
signatures: signing and signature metadata
comments/notes: comments, footnotes/endnotes
export/render: export (including Docling, signed PDF, and XPS advanced export), page rendering
Use add_chart_end with chart_type="column" or "waterfall", a shared categories list, and series objects containing name and numeric values matching the categories. Waterfall series also require a matching is_subtotal boolean array. Use the zero-based chartIndex and seriesIndex values from list_charts to select charts and series. format_chart_plot_area accepts a solid fill_color or a one-color gradient object, plus optional line_color and line_width_points; colors use six-digit RGB hex, and omitted formatting fields retain their values. get_waterfall_totals inspects all points in the selected waterfall series, or a single zero-based point_index.
Example Workflow via an MCP Client
Sequence of tool calls (names match the server):
create_document→ getdoc_idadd_heading(e.g., levels 1–3)add_paragraph/insert_text_endadd_table_endoradd_table_at_paragraphadd_watermark_textoradd_watermark_image_base64export_base64(e.g.,fmt="pdf") — get file as Base64
Integration with MCP Clients
Claude Desktop MCP: add this server with
streamable-httporssetransport and the URL printed by the server at startup.Any MCP (JSON) clients — configure the matching transport and path.
License
This package is licensed under the MIT License. However, it depends on Aspose.Words for Python via .Net library, which is proprietary, closed-source library.
⚠️ You must obtain valid license for Aspose.Words for Python via .Net library. This repository does not include or distribute any proprietary components.
Trademarks
This project may contain trademarks or logos for projects, products, or services. Use of third-party trademarks or logos is subject to those third-party policies.
Available Tools
93 toolsadd_bookmark_at_paragraphC
Add a bookmark to the specified paragraph
Inputs: doc_id (required), name (required), paragraph_index (required).
add_endnoteC
Add an endnote to a paragraph
Inputs: doc_id (required), paragraph_index (required), text (required).
add_endnote_by_anchorC
Add an endnote after/before the anchor text
Inputs: doc_id (required), anchor_text (required), text (required), position, +3 more.
add_footnoteC
Add a footnote to a paragraph
Inputs: doc_id (required), paragraph_index (required), text (required).
add_footnote_by_anchorC
Add a footnote after/before the anchor text
Inputs: doc_id (required), anchor_text (required), text (required), position, +3 more.
add_header_textC
Add text to the header
Inputs: doc_id (required), text (required), primary.
add_headingC
Add a heading with level and font options
Inputs: doc_id (required), text (required), level, font_name, +4 more.
add_page_break_at_paragraphC
Insert a page break before the specified paragraph
Inputs: doc_id (required), paragraph_index (required).
add_page_break_endC
Insert a page break at the end of the document
Inputs: doc_id (required).
add_page_break_startC
Insert a page break at the start of the document
Inputs: doc_id (required).
add_page_numberingC
Insert page numbering into headers/footers
Inputs: doc_id (required), format_string.
add_paragraphC
Add a paragraph with optional style and formatting
Inputs: doc_id (required), text (required), style, font_name, +4 more.
add_picture_base64_endB
Add an image (base64) at the end of the document
Inputs: doc_id (required), image_base64 (required), width_points, height_points, +1 more.
add_picture_base64_startC
Add an image (base64) at the start of the document
Inputs: doc_id (required), image_base64 (required), width_points, height_points, +1 more.
add_table_at_paragraphC
Add a table at the specified paragraph
Inputs: doc_id (required), rows (required), cols (required), paragraph_index (required), +2 more.
add_table_endC
Add a table at the end of the document
Inputs: doc_id (required), rows (required), cols (required), data, +1 more.
add_table_startC
Add a table at the start of the document
Inputs: doc_id (required), rows (required), cols (required), data, +1 more.
add_watermark_image_base64C
Add an image watermark from base64
Inputs: doc_id (required), image_base64 (required), scale, washout.
add_watermark_textC
Add a text watermark
Inputs: doc_id (required), text (required), font_name, size, +2 more.
apply_table_alternating_rowsC
Apply alternating row colors to a table
Inputs: doc_id (required), table_index (required), color1, color2.
auto_fit_table_columnsC
Auto fit table columns to content
Inputs: doc_id (required), table_index (required).
convert_footnotes_to_endnotesB
Convert all footnotes to endnotes
Inputs: doc_id (required).
copy_documentC
Create a copy of the document and return the new ID
Inputs: doc_id (required).
create_custom_styleC
Create a custom style with font properties
Inputs: doc_id (required), style_name (required), bold, italic, +4 more.
create_documentC
Create a new document and return its ID
Inputs: name.
delete_documentC
Delete a document from the store
Inputs: doc_id (required).
delete_endnotes_by_anchorB
Delete endnotes by anchor text (with filter options)
Inputs: doc_id (required), anchor_text (required), occurrence, remove_all, +2 more.
delete_footnotes_by_anchorC
Delete footnotes by anchor text (with filter options)
Inputs: doc_id (required), anchor_text (required), occurrence, remove_all, +2 more.
delete_paragraphC
Delete a paragraph by index
Inputs: doc_id (required), paragraph_index (required).
export_base64C
Export the document to the specified format and return as base64
Inputs: doc_id (required), fmt.
export_base64_advancedD
Advanced export with additional format options
Inputs: doc_id (required), fmt (required), options.
find_textC
Find text occurrences in the document
Inputs: doc_id (required), text (required), match_case, whole_word.
format_tableC
Apply composite formatting to a table
Inputs: doc_id (required), table_index (required), has_header_row, border_style, +1 more.
format_table_cell_textC
Set text and formatting of a specific table cell
Inputs: doc_id (required), table_index (required), row_index (required), col_index (required), +7 more.
format_textB
Format text within a paragraph by character range
Inputs: doc_id (required), paragraph_index (required), start_pos (required), end_pos (required), +6 more.
get_all_commentsC
Get all document comments
Inputs: doc_id (required).
get_all_notesC
Get a list of all document notes
Inputs: doc_id (required).
get_comments_by_authorC
Get comments by author
Inputs: doc_id (required), author (required).
get_comments_for_paragraphC
Get comments for the specified paragraph
Inputs: doc_id (required), paragraph_index (required).
get_digital_signaturesC
Get document digital signature metadata
Inputs: doc_id (required).
get_document_base64C
Get the document binary content as base64
Inputs: doc_id (required).
get_infoC
Get general document information
Inputs: doc_id (required).
get_outlineC
Get the document outline (headings structure)
Inputs: doc_id (required).
get_propertiesB
Read document properties (Title, Author, etc.)
Inputs: doc_id (required).
get_textC
Get the full document text as a single block
Inputs: doc_id (required).
get_xmlC
Get the document XML
Inputs: doc_id (required).
healthC
Health check
Inputs: no named parameters.
highlight_table_headerC
Highlight the table header row
Inputs: doc_id (required), table_index (required), header_color, text_color.
insert_header_near_textC
Insert a heading near the found text or paragraph index
Inputs: doc_id (required), target_text, header_title, position, +2 more.
insert_html_at_paragraphC
Insert HTML at the specified paragraph
Inputs: doc_id (required), html (required), paragraph_index (required).
insert_html_endC
Insert HTML at the end of the document
Inputs: doc_id (required), html (required).
insert_html_startC
Insert HTML at the start of the document
Inputs: doc_id (required), html (required).
insert_hyperlink_at_paragraphC
Insert a hyperlink at the specified paragraph
Inputs: doc_id (required), paragraph_index (required), text (required), target (required), +1 more.
insert_line_or_paragraph_near_textC
Insert a line/paragraph near the found text
Inputs: doc_id (required), target_text, line_text, position, +1 more.
insert_list_at_paragraphC
Insert a list at the specified paragraph
Inputs: doc_id (required), items (required), paragraph_index (required), kind.
insert_list_endC
Insert a bulleted or numbered list at the end
Inputs: doc_id (required), items (required), kind.
insert_list_startC
Insert a bulleted or numbered list at the start
Inputs: doc_id (required), items (required), kind.
insert_markdown_at_paragraphC
Insert Markdown at the specified paragraph
Inputs: doc_id (required), markdown (required), paragraph_index (required).
insert_markdown_endC
Insert Markdown at the end of the document
Inputs: doc_id (required), markdown (required).
insert_markdown_startC
Insert Markdown at the start of the document
Inputs: doc_id (required), markdown (required).
insert_numbered_list_near_textC
Create a numbered or bulleted list near text
Inputs: doc_id (required), target_text, list_items, position, +2 more.
insert_section_breakC
Insert a section break of the specified type
Inputs: doc_id (required), kind.
insert_text_at_paragraphC
Insert text into the specified paragraph by index
Inputs: doc_id (required), text (required), paragraph_index (required).
insert_text_endC
Insert text at the end of the document
Inputs: doc_id (required), text (required).
insert_text_startC
Insert text at the start of the document
Inputs: doc_id (required), text (required).
list_documentsB
List all available documents
Inputs: no named parameters.
merge_documentsC
Merge multiple documents into one
Inputs: source_doc_ids (required), append_document_with_new_page, resolve_theme_colors.
merge_table_cellsC
Merge a range of table cells
Inputs: doc_id (required), table_index (required), start_row (required), start_col (required), +2 more.
merge_table_cells_horizontalC
Merge cells horizontally in a row
Inputs: doc_id (required), table_index (required), row_index (required), start_col (required), +1 more.
merge_table_cells_verticalD
Merge cells vertically in a column
Inputs: doc_id (required), table_index (required), col_index (required), start_row (required), +1 more.
notes_styleC
Set text style for footnotes/endnotes
Inputs: doc_id (required), font_name, font_size, bold, +2 more.
protect_documentC
Protect the document with a password
Inputs: doc_id (required), password.
protect_restrictC
Restrict editing ranges in the document
Inputs: doc_id (required), password, ranges.
read_paragraphsC
Read a range of paragraphs from the document
Inputs: doc_id (required), start, end.
render_page_base64C
Render a document page to an image/base64
Inputs: doc_id (required), page_index, fmt, dpi.
replace_textC
Replace text in the document with case/scope and regex options
Inputs: doc_id (required), find_text, replace_text, search_text, +9 more.
save_as_newC
Save a copy of the document with a new name and format
Inputs: doc_id (required), name (required), fmt.
set_page_setupB
Set page setup: margins, orientation, paper, columns
Inputs: doc_id (required), margins, orientation, paper, +1 more.
set_propertiesC
Set document properties (Title, Author, etc.)
Inputs: doc_id (required), title, author, subject, +1 more.
set_table_alignment_allC
Align the entire table relative to the page
Inputs: doc_id (required), table_index (required), horizontal.
set_table_cell_alignmentC
Set table cell horizontal/vertical alignment
Inputs: doc_id (required), table_index (required), row_index (required), col_index (required), +2 more.
set_table_cell_paddingC
Set table cell padding
Inputs: doc_id (required), table_index (required), row_index (required), col_index (required), +4 more.
set_table_cell_shadingC
Set table cell shading to the specified color
Inputs: doc_id (required), table_index (required), row_index (required), col_index (required), +1 more.
set_table_column_widthC
Set a table column width
Inputs: doc_id (required), table_index (required), col_index (required), width (required), +1 more.
set_table_column_widthsC
Set all table column widths
Inputs: doc_id (required), table_index (required), widths (required), width_type.
set_table_widthC
Set the overall table width
Inputs: doc_id (required), table_index (required), width (required), width_type.
sign_documentC
Sign the document with a digital certificate
Inputs: doc_id (required), certificate_path (required), certificate_passphrase, application_version, +5 more.
statsC
Get document statistics (pages, words, etc.)
Inputs: doc_id (required).
unprotect_documentC
Unprotect the document
Inputs: doc_id (required), password.
validate_endnotes_by_anchorC
Validate that at least the specified number of endnotes exist by anchor
Inputs: doc_id (required), anchor_text (required), min_count, match_case, +1 more.
validate_footnotes_by_anchorC
Validate that at least the specified number of footnotes exist by anchor
Inputs: doc_id (required), anchor_text (required), min_count, match_case, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 93 tools
Several tool families overlap heavily: export_base64, export_base64_advanced, save_as_new, and get_document_base64 all produce document output, while insert_list_start, insert_list_end, insert_list_at_paragraph, and insert_numbered_list_near_text are near-duplicates. Add_footnote vs add_footnote_by_anchor and protect_restrict vs protect_document further blur boundaries, making tool selection risky.
Most tools follow a readable verb_noun pattern like create_document, insert_text_end, and delete_paragraph. However, there are notable deviations: bare nouns like stats, health, and notes_style, double-verb protect_restrict, and inconsistent positional suffixes (_end, _start, _at_paragraph, _near_text) throughout the set.
With 93 tools, this server far exceeds the 25+ threshold and presents an overwhelming selection surface. The count is inflated by micro-variants of the same operations, such as start/end/at_paragraph/near_text versions of the same insertion actions.
The server covers an impressively broad range of document operations: creation, insertion, tables, footnotes, protection, exports, and metadata. However, lifecycle coverage is uneven: comments are read-only, and watermarks, headers, bookmarks, and hyperlinks have add/insert operations but no corresponding delete/update tools.
Maintenance
Related MCP Connectors
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Generate PDF, Word (.docx) and PowerPoint (.pptx) documents from Markdown over MCP.
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
A remote MCP server to convert HTML documents (URL or raw source) to PDF or screenshots
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that enables programmatic interaction with Microsoft Word documents on Windows via COM Interop, allowing operations like document creation, text manipulation, formatting, and table management.16MIT
- 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
- AlicenseAqualityDmaintenanceMCP server for Word document (.docx) creation and manipulation — the production-grade document automation tool for AI agents.955 npmMIT
- FlicenseAqualityDmaintenanceMCP server for generating professionally formatted Word documents (.docx). Supports corporate templates (colors, fonts, logo), headers/footers, and Markdown conversion.4-