Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

docx4j Word documents

by plutextversion 0.2.0i★ –iRuns on your computer
Registry nameio.github.plutext/docx4j-mcp

Install

Overview

Description from the maker (original English)

Read, convert and fill Word (.docx) documents: templates, Markdown/HTML in and out, PDF with math.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs on your computer
  • Transport: stdio
  • Category: Docs, sheets & office work

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on your computer with your user’s permissions (files, network, apps).
  • The registry lists no key to fill in.

You need

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Download the maker’s .mcpb file

The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.

Run this in your terminal

claude mcp add docx4j -- docker run -i --rm ghcr.io/plutext/docx4j-mcp:0.2.0

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "docx4j": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/plutext/docx4j-mcp:0.2.0"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "docx4j": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/plutext/docx4j-mcp:0.2.0"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account plutext, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Docs, sheets & office worki

  • More stars than 0% of the other 2198 servers in this category
  • Published to the registry more recently than 35% of the other 2198 servers in this category
  • Basic checks equal to or better than 100% of the other 2198 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is docx4j Word documents safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 2 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB, Docker on your computer.

What can I use instead?

In the same category: Agent-Native Calendar, Excel MCP Server, MCP Server for Excel

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Agent-Native Google Calendar - manage events, sync, and public booking

Runs in the cloud★ 7,620MITUpdated 2 months ago
Install

Excel MCP Server

by haris-musa

Lets AI create and edit Excel files itself, including formulas, charts and PivotTables, without Excel installed.

Runs on your computer★ 4,276MITUpdated 6 days ago
Install

Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.

Runs on your computer★ 847MITUpdated 4 days ago
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

docx4j-mcp

A Model Context Protocol server that exposes docx4j's engine to AI agents: read, convert and fill Word (.docx) documents from Claude Desktop, Claude Code, or any MCP client.

Engine: docx4j 17.1.0 (the server versions independently; the bundled docx4j version is in the pom, the server's startup log, and its MCP instructions).

MCP protocol: 2025-11-25 (Java SDK 2.0.1, the newest available). Clients speaking the 2026-07-28 spec work if they implement its dual-era fallback: the server/discover probe gets a clean JSON-RPC -32601 and the client falls back to initialize (verified over stdio). A modern-only client with no fallback cannot connect until the SDK's 2026-07-28 support (milestone 2.2) ships, at which point this server will migrate.

Status: phase 3 — all tools work over stdio against released docx4j 17.0.4; packaged as a runnable jar, an .mcpb bundle, an OCI image and a Claude Code plugin. The plan, tool surface and phasing are in CR-mcp-server.md.

Build

Requires JDK 17+. All docx4j dependencies (docx4j 17.1.0, ImportXHTML 17.0.4) come from Maven Central.

mvn package            # -> target/docx4j-mcp.jar (shaded, runnable)

mvn test # JUnit 5 tests against the tool handlers directly

Run

java -jar target/docx4j-mcp.jar --root /path/to/documents [--root ...] [--max-inline-chars N]

Bare directory arguments are also accepted as roots (this is what the .mcpb bundle's folder picker passes).

Claude Desktop, one click

Install docx4j-mcp.mcpb from the GitHub release (Settings → Extensions), pick the folders the server may touch, done. Built locally with packaging/build-mcpb.sh. Requires Java 17+ on your PATH.

Docker
docker run -i --rm -v /path/to/documents:/data ghcr.io/plutext/docx4j-mcp

(paths in tool calls are then container paths under /data; packaging/docker/Dockerfile to build locally).

Claude Code plugin

packaging/claude-plugin/ bundles the server config and a skill for the template/authoring workflows. Set DOCX4J_MCP_JAR (path to the jar) and optionally DOCX4J_MCP_ROOTS.

Releasing

Tag vX.Y.Z: .github/workflows/release.yml builds jar + mcpb, attaches them to the GitHub release, pushes ghcr.io/plutext/docx4j-mcp, and publishes server.json (sha filled in) to the official MCP registry via GitHub OIDC.

Every file path an agent passes must resolve inside one of the --root directories (symlinks are resolved first). There is no default root; the server refuses to start without one. Logging goes to stderr; stdout is the protocol. Tools that return text inline cap it at --max-inline-chars (default 200000) and otherwise write to output_path or truncate with a marker.

Claude Code (.mcp.json in your project)
{

"mcpServers": { "docx4j": { "command": "java", "args": ["-jar", "/path/to/docx4j-mcp.jar", "--root", "/path/to/documents"] } } }

Claude Desktop (claude_desktop_config.json)
{

"mcpServers": { "docx4j": { "command": "java", "args": ["-jar", "/path/to/docx4j-mcp.jar", "--root", "/Users/you/Documents"] } } }

Tools

ToolWhat it does
describe_templateWhat data a template wants: skeleton XML + xpaths/conditions (OpenDoPE, bound content controls) or MERGEFIELD names and format switches (mail merge). Call before fill_template.
fill_templateFill a template, preserving its formatting. data is an XML string (OpenDoPE / bound controls; repeats and conditions processed) or a JSON object (mail merge).
convert_to_pdfdocx → PDF via XSL-FO / Apache FOP; equations and WMF/EMF drawings rendered as vectors; optional update_toc; reports font substitutions. Bundles metric-compatible fonts (Carlito, Caladea, Liberation, Tinos…).
markdown_to_docxMarkdown → properly styled docx (headings, numbering, GFM tables, footnotes, task lists, TeX math). Optional styles_template_path.
docx_to_markdowndocx → Markdown (structure preserved). Options: tracked_changes accept/markup, image_dir_path.
html_to_docxHTML → docx via docx4j-ImportXHTML. Loose HTML accepted (normalised with jsoup); h1–h6 map to heading styles; optional styles_template_path; mode: altchunk embeds the HTML for Word to convert on open. Remote images/stylesheets are never fetched.
convert_to_htmldocx → standalone HTML (visitor exporter; image_dir_path for images; optional update_toc).
extract_textPlain text, one line per paragraph/table.

Mathematics is supported end to end: TeX math in Markdown ($..$) and MathML in HTML become real, editable Word equations (OMML), and equations render in PDF (via jeuclid/FOP, no LaTeX toolchain) and HTML (native MathML, no JavaScript) output. Known limitation: a very long single display equation is one atomic graphic in PDF and does not line-wrap.

Writers take output_path and refuse to overwrite unless overwrite: true.

Example (Claude Code)

Use describe_template on contracts/nda-template.docx, then fill it for Acme Pty Ltd and

write contracts/nda-acme.docx, then convert that to PDF.

The agent gets the skeleton XML (or MERGEFIELD names), fills it, and calls fill_template and convert_to_pdf; the results tell it what was written and which fonts were substituted.

Licence

Apache License 2.0.

Ask PopNx