Summary
If you're building AI workflows that need to edit existing Word documents without breaking formatting, this gives your MCP client surgical tools for the job. It exposes read_file to parse docx into stable paragraph IDs, grep to locate text, replace_text for pinpoint edits, and save to write both clean and tracked changes outputs. The architecture is TypeScript native, no Python or LibreOffice required. You get comment and footnote support, revision extraction as JSON, and compare_documents for diff workflows. It's built for the specific pain point where an agent proposes contract or document changes and you need deterministic, formatting-preserving edits that a human can review in Word's track changes.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Safe Docx
Edit Word and OpenDocument files with coding agents.
English · Español · 简体中文 · Português · Deutsch
Safe Docx is a local MCP server and CLI for reading, searching, editing, comparing, converting, and saving document files. It preserves DOCX structure and can produce clean or tracked-changes output.
Example
Ask your coding agent:
Edit NDA.docx. Change the governing law from New York to Delaware.
Save a clean copy and a tracked-changes copy. Do not change anything else.
Safe Docx finds the clause, applies the targeted edit, and writes both files for review. The rest of the document stays outside the requested edit.
Follow the complete editing walkthrough.
Comparisons
Install
npm install --global @usejunior/safe-docx
Then configure your MCP client with the installed executable's absolute path. For Claude Code:
claude mcp add safe-docx -- /absolute/path/to/safe-docx
Antigravity CLI
Add Safe Docx to ~/.gemini/config/mcp_config.json:
{
"mcpServers": {
"safe-docx": {
"command": "/absolute/path/to/safe-docx",
"args": []
}
}
}
Restart agy, then ask it to edit a .docx file. Antigravity may ask you to approve the MCP server before first use.
See Installation and verification for locating the executable, pinning a version, and configuring clients.
Documentation
- Installation and verification
- Tool reference
- TypeScript library
- Architecture
- Testing and evidence
- Trust and conformance
- Contributing
Standards Conformance
Browse the Safe Docx Conformance Explorer to navigate ECMA-376 sections, OOXML schema declarations, capability claims, explicit non-goals, and measured cross-implementation outcomes.
The generated repository conformance report remains the source-controlled record of targeted sections, non-goals, and verification references.
What Safe Docx Is Not Optimized For
Safe Docx is not a visual editor or layout engine. It does not provide browser rendering, real-time collaboration, or pixel-level pagination guarantees. .dotx templates must be converted to .docx before use.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Registryactive
Package@usejunior/safe-docx
TransportSTDIO
UpdatedApr 28, 2026
