Files and documents · MCP server
Safe Docx: MCP server, setup and security
Safe Docx is an open-source MCP server that lets an AI agent edit existing Word documents while preserving formatting and tracking changes. Its repository has 46 stars and its last commit is from October 22, 2026 and it is licensed under Apache-2.0.
| Adoption (stars) | 17/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 20/30 |
What Safe Docx does
According to its repository: “Edit existing Word .docx files with formatting preservation, tracked changes, comments, footnotes and document comparison.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Safe Docx is listed under Files and documents, a category of 55 servers in the directory, where it ranks #33 by stars.
Topics declared by the repository: gemini-cli-extension.
Installing and connecting Safe Docx
Distribution modes declared in the official MCP registry:
- npm package (Node.js, usually started with
npx)
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript. Listed systems: macOS, Windows, Linux.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for Safe Docx:
- System access: the Files and documents category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on February 20, 2026, the UseJunior/safe-docx repository has 46 stars and 7 forks, with 87 open issues. It has more stars than 50% of the servers in the directory. It received changes this month. Version published in the registry: 0.25.0 (October 9, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Safe Docx is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (Apache-2.0)
Avoid if…
- You cannot isolate the agent (sandbox, container)
Alternatives
- Markitdown191.9K ★
- Puter43.9K ★
- Filestash14.8K ★
- RevoGrid DataGrid MCP3.5K ★
- Mu436 ★
- Everything Search367 ★
Learn more
Frequently asked questions
How do I install Safe Docx?
Safe Docx is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of UseJunior/safe-docx.
Is Safe Docx free?
The code is published under the Apache-2.0 licence and can be used free of charge.
Is Safe Docx safe?
Points to watch: system access. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by UseJunior on GitHub. Check who maintains it before giving it access.
What are the alternatives to Safe Docx?
In the same category: Markitdown, Puter, Filestash, and RevoGrid DataGrid MCP. Markitdown and Puter score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score