PluginBench
MCP Server
Maintained
MIT

Word MCP Live MCP Server

io.github.ykarapazar/word-mcp-live

Live Microsoft Word editing with tracked changes, comments, and 124 tools—edit while documents are open.

What is the Word MCP Live MCP server?

The Word MCP Live server enables AI assistants to edit Microsoft Word documents in real-time while they're open, with native tracked changes, comments, and undo support. It provides 124 tools across cross-platform and live editing modes, working on Windows, macOS, and Linux.

Word MCP Live gives Claude, Cursor, and other MCP-compatible AI assistants full control over Word documents. Changes appear live in your open document with real tracked changes, threaded comments, and per-action undo. No save-close-reopen cycles—just tell the AI what you need and watch it happen. Works cross-platform for file operations and on Windows/macOS for live editing.

How to install Word MCP Live

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • MCP_AUTHOR

    Author name shown on tracked changes and comments (default: AI Assistant)

  • MCP_AUTHOR_INITIALS

    Author initials shown on comments (default: AI)

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "word-mcp-live": {
      "command": "uvx",
      "args": [
        "word-mcp-live"
      ],
      "env": {
        "MCP_AUTHOR": "<YOUR_MCP_AUTHOR>",
        "MCP_AUTHOR_INITIALS": "<YOUR_MCP_AUTHOR_INITIALS>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • get_document_text — Read document text and paragraph styles
  • word_live_replace_text — Find and replace text with optional tracked changes
  • add_comment — Add comments anchored to specific text
  • set_paragraph_formatting — Apply formatting to paragraphs (bold, italic, font, size, style)
  • insert_table — Insert tables into documents
  • add_tracked_change — Create tracked changes for edits
  • list_comments — Retrieve all comments from a document
  • delete_comment — Remove comments from a document
  • insert_header_footer — Add headers and footers with page numbers
  • set_page_layout — Configure page size, orientation, and margins
  • insert_table_of_contents — Generate automatic table of contents
  • insert_cross_reference — Add cross-references to headings and bookmarks
  • insert_equation — Insert mathematical formulas
  • add_bookmark — Create bookmarks for navigation
  • list_revisions — Retrieve tracked changes from a document

Use cases

  • Draft contracts with tracked changes for colleague review
  • Format documents with consistent styles, fonts, and automatic numbering
  • Add threaded comments and resolve feedback during collaborative review
  • Find and replace text across documents while maintaining tracked changes
  • Generate professional layouts with headers, footers, page numbers, and tables of contents
  • Insert equations, cross-references, and bookmarks for technical or academic documents

Word MCP Live MCP server FAQ

What is Word MCP Live?

Word MCP Live is an MCP server that lets AI assistants like Claude and Cursor edit Microsoft Word documents live while they're open. Changes appear instantly with real tracked changes, comments, and full undo support—no save-close-reopen cycles needed.

Is it free?

Yes, Word MCP Live is open-source under the MIT License and free to use.

How do I install it in Cursor?

Click the one-click install button at the top of the GitHub repo, or manually add the configuration to ~/.cursor/mcp.json with command 'uvx' and args ['word-mcp-live']. Set MCP_AUTHOR and MCP_AUTHOR_INITIALS environment variables for your name on tracked changes.

How do I install it in Claude Desktop?

Add the server to your claude_desktop_config.json with command 'uvx' and args ['word-mcp-live']. Include MCP_AUTHOR and MCP_AUTHOR_INITIALS environment variables. Restart Claude Desktop.

Does it require Microsoft Word to be installed?

Live editing (while Word is open) requires Word on Windows or macOS. Cross-platform tools for reading/writing .docx files work on Windows, macOS, and Linux without Word installed.

What authentication is required?

No authentication is required. The server runs entirely on your local machine with no data collection or transmission. Set MCP_AUTHOR and MCP_AUTHOR_INITIALS as environment variables to customize your name on tracked changes and comments.

README (reference)

Source of truth, from the repository.

<div align="center">

Install in Cursor

word-mcp-live

The only MCP server that edits Word documents while they're open

Live editing · Tracked changes · Per-action undo · 124 tools · Cross-platform

PyPI Python 3.11+ License: MIT Platform: Windows + macOS/Linux

</div>

word-mcp-live gives any AI assistant that supports MCP full control of Microsoft Word. Open a document, tell the AI what you need, and watch it happen — formatting, tracked changes, comments, and all. Changes appear live in your open document.

<table> <tr> <td width="50%">

Without word-mcp-live

  • AI can discuss your document but can't touch it
  • You copy-paste between AI and Word, losing formatting
  • Track changes? You do those manually after the fact
  • Every edit means save → close → process → reopen
</td> <td width="50%">

With word-mcp-live

  • "Add a tracked change replacing ABC Corp with XYZ Ltd" — done
  • Changes appear live in your open Word document
  • Every AI edit is one Ctrl+Z away
  • Real tracked changes with your name, not XML hacks
</td> </tr> </table>

See it in action

https://github.com/user-attachments/assets/fbb09af4-1e25-4e49-94d0-45b363278810

What Sets This Apart

  • Live editing — Edit documents while they're open in Word. No save-close-reopen cycle.
  • Full undo — Every AI action is a single Ctrl+Z. Made a mistake? Just undo it.
  • Native tracked changes — Real Word revisions with your name, not XML hacks.
  • Threaded comments — Add, reply, resolve, and delete comments like a human reviewer.
  • Layout diagnostics — Detects formatting problems before they become print disasters.
  • Equations & cross-references — Insert math formulas and auto-updating references.
  • 124 tools — The most comprehensive Word MCP server available.

Quick Start

pip install word-mcp-live

Or install from source:

git clone https://github.com/ykarapazar/word-mcp-live.git
cd word-mcp-live
pip install -e .

Client Installation

<details open> <summary><b>Claude Desktop</b></summary>

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "word": {
      "command": "uvx",
      "args": ["word-mcp-live"],
      "env": {
        "MCP_AUTHOR": "Your Name",
        "MCP_AUTHOR_INITIALS": "YN"
      }
    }
  }
}
</details> <details> <summary><b>Claude Code</b></summary>

Add to your .mcp.json:

{
  "mcpServers": {
    "word": {
      "command": "uvx",
      "args": ["word-mcp-live"],
      "env": {
        "MCP_AUTHOR": "Your Name",
        "MCP_AUTHOR_INITIALS": "YN"
      }
    }
  }
}
</details> <details> <summary><b>Cursor</b></summary>

One-click: Click the install button at the top of this page.

Manual: Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "word": {
      "command": "uvx",
      "args": ["word-mcp-live"],
      "env": {
        "MCP_AUTHOR": "Your Name",
        "MCP_AUTHOR_INITIALS": "YN"
      }
    }
  }
}
</details> <details> <summary><b>VS Code / Copilot</b></summary>

One-click: Install in VS Code

Manual: Add to your VS Code settings.json:

{
  "mcp": {
    "servers": {
      "word": {
        "command": "uvx",
        "args": ["word-mcp-live"],
        "env": {
          "MCP_AUTHOR": "Your Name",
          "MCP_AUTHOR_INITIALS": "YN"
        }
      }
    }
  }
}
</details> <details> <summary><b>Windsurf</b></summary>

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "word": {
      "command": "uvx",
      "args": ["word-mcp-live"],
      "env": {
        "MCP_AUTHOR": "Your Name",
        "MCP_AUTHOR_INITIALS": "YN"
      }
    }
  }
}
</details> <details> <summary><b>Docker</b></summary>
{
  "mcpServers": {
    "word": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/ykarapazar/word-mcp-live"],
      "env": {
        "MCP_AUTHOR": "Your Name",
        "MCP_AUTHOR_INITIALS": "YN"
      }
    }
  }
}

Note: Docker mode supports cross-platform tools only. Live editing requires a native Windows install.

</details>

MCP_AUTHOR sets your name on tracked changes and comments (default: "Author"). MCP_AUTHOR_INITIALS sets comment initials.

Two Modes

Works everywhereLive editing (Word open)
What it doesCreate and edit saved .docx filesEdit documents live while you work in Word
PlatformWindows, macOS, LinuxWindows (COM) and macOS (JXA)
UndoFile-level savesPer-action Ctrl+Z (Windows); per-operation undo (macOS)
Best forBatch processing, document generationInteractive editing, formatting, review

Both modes work together. The AI picks the right one for the task.

macOS Live Editing (New in v1.5.0)

Live tools now work on macOS via JavaScript for Automation (JXA). Same tool names, same parameters — the server detects your platform and uses the right automation backend.

FeatureWindowsmacOS
Text read/write/find/replaceCOMJXA
Formatting (bold, font, style)COMJXA
Track changes & revisionsCOMJXA
Comments (add, delete, list)COMJXA
Tables (read, write, add rows)COMJXA
Page layout, headers, bookmarksCOMJXA
Equations, cross-referencesCOMJXA
Threaded comment repliesCOMNot available
Comment resolve/unresolveCOMNot available
Undo history inspectionCOMNot available
WatermarksCOMNot available

Configuration

VariableDefaultDescription
MCP_AUTHOR"Author"Author name for tracked changes and comments
MCP_AUTHOR_INITIALS""Author initials for comments
MCP_TRANSPORTstdioTransport type: stdio, sse, or streamable-http
MCP_HOST0.0.0.0Host to bind (for SSE/HTTP transports)
MCP_PORT8000Port to bind (for SSE/HTTP transports)

For remote deployment, see RENDER_DEPLOYMENT.md.

Example Prompts

Just tell the AI what you want in plain language:

"Draft a contract with tracked changes so my colleague can review"
"Format all headings as Cambria 13pt bold and add automatic numbering"
"Add a comment on paragraph 3 asking about the deadline"
"Find every mention of 'ABC Corp' and replace with 'XYZ Ltd' as a tracked change"
"Set the page to A4 landscape with 2cm margins"
"Insert a table of contents based on the document headings"
"Add page numbers in the footer and our company name in the header"
"Insert a cross-reference to Heading 2 in paragraph 5"

Usage Examples

Example 1: Read a document (cross-platform)

Tool call: get_document_text

{ "filename": "C:/Documents/report.docx" }

Expected output:

{
  "status": "success",
  "paragraphs": [
    {"index": 0, "text": "Quarterly Report", "style": "Heading 1"},
    {"index": 1, "text": "Revenue increased by 15% compared to Q3.", "style": "Normal"},
    {"index": 2, "text": "Key Metrics", "style": "Heading 2"}
  ],
  "total_paragraphs": 3
}

Example 2: Live editing with tracked changes (Windows)

Tool call: word_live_replace_text

{
  "filename": "report.docx",
  "find_text": "ABC Corporation",
  "replace_text": "XYZ Ltd",
  "match_case": true,
  "replace_all": true,
  "track_changes": true
}

Expected output:

{
  "status": "success",
  "replacements": 4,
  "message": "Replaced 4 occurrences (tracked changes enabled)"
}

The replacements appear as tracked changes in Word with strikethrough on "ABC Corporation" and underline on "XYZ Ltd".

Example 3: Add a comment anchored to text (cross-platform)

Tool call: add_comment

{
  "filename": "C:/Documents/contract.docx",
  "target_text": "payment within 30 days",
  "comment_text": "Should we extend this to 45 days?",
  "author": "Jane Smith"
}

Expected output:

{
  "status": "success",
  "message": "Comment added by Jane Smith on 'payment within 30 days'"
}

The comment appears in Word's Review panel, anchored to the specified text.

Tool Reference

124 tools across two modes — see the complete tool reference for details.

CategoryCount
Cross-platform (python-docx)80
Windows Live (COM automation)44
macOS Live (JXA automation)40 (of the 44 live tools)

Requirements

  • Python 3.11+
  • python-docx, fastmcp, msoffcrypto-tool (installed automatically)
  • Windows Live tools: Windows 10/11 + Microsoft Word + pywin32 (installed automatically)
  • macOS Live tools: macOS + Microsoft Word for Mac (uses built-in JXA — no extra dependencies)

The cross-platform tools work without Word installed — only python-docx is needed.

Contributing

See CONTRIBUTING.md for development setup, code style, and how to add new tools.

Found a bug? Open an issue. Have an idea? Request a feature.

Acknowledgments

Built on top of GongRzhe/Office-Word-MCP-Server by GongRzhe (MIT License).

Additional libraries: python-docx · FastMCP · pywin32

Privacy

This server runs entirely on your local machine. No data is collected, transmitted, or stored. See the full Privacy Policy.

Support

License

MIT License — see LICENSE for details.

Star History

<a href="https://star-history.com/#ykarapazar/word-mcp-live&Date"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=ykarapazar/word-mcp-live&type=Date&theme=dark" /> <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=ykarapazar/word-mcp-live&type=Date" /> <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=ykarapazar/word-mcp-live&type=Date" /> </picture> </a> <!-- mcp-name: io.github.ykarapazar/word-mcp-live -->

Related MCP servers

Create and manage events in seconds from your AI assistant. No account needed.

0
TypeScript
MIT
View repository →

Verified behind-the-meter data center power, announcements, and provenance receipts.

0
Python
MIT
View repository →

Persistent, Solana-aware project memory for AI coding agents. Typed entities + git-aware diffs.

1
TypeScript
MIT
View repository →

SEC EDGAR filings, XBRL financials, FRED economic data, and real-time market quotes

1
TypeScript
MIT
View repository →

Polymarket, GDELT, OpenSky, Cloudflare Radar unified as one MCP server.

0
Python
MIT
View repository →

Live webcast transcription + vocal stress analysis (F0 jitter, hesitation) for earnings calls.

1
Python
MIT
View repository →