Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

docx4j Word documents

OCI · GHCR.IO/PLUTEXT/DOCX4J-MCP:0.2.0 · 2 COMPONENTS · SCANNED SEP 20

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

+6 this week 43 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency32
Schema Quality & AI Usability70
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1693 tokens (~211/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the docx4j Word documents MCP server?

docx4j Word documents runs locally as a container image, launched with docker run --rm -i ghcr.io/plutext/docx4j-mcp:0.2.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/plutext/docx4j-mcp:0.2.0

# add to Claude Code
claude mcp add plutext-docx4j-mcp -- docker run --rm -i ghcr.io/plutext/docx4j-mcp:0.2.0
// .cursor/mcp.json
{
  "mcpServers": {
    "plutext-docx4j-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/plutext/docx4j-mcp:0.2.0"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "plutext-docx4j-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/plutext/docx4j-mcp:0.2.0"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add plutext-docx4j-mcp -- docker run --rm -i ghcr.io/plutext/docx4j-mcp:0.2.0
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "plutext-docx4j-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/plutext/docx4j-mcp:0.2.0"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  plutext-docx4j-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/plutext/docx4j-mcp:0.2.0"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "plutext-docx4j-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/plutext/docx4j-mcp:0.2.0"
      ]
    }
  }
}
// mcp.json
{
  "mcpServers": {
    "plutext-docx4j-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/plutext/docx4j-mcp:0.2.0"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +4
    • Stability: unverified → 0.27 functional
  • 8 Sept 26 37

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed oci/ghcr.io/plutext/docx4j-mcp:0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 8 exposed · ~1,549 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
convert_to_html ~223

Renders a Word document to a standalone HTML page (CSS from the document's styles, fonts mapped to web font stacks); Word equations become native, accessible MathML (no JavaScript). For a lossless-ish text view prefer docx_to_markdown; use this when the layout/formatting matters or the HTML will be shown in a browser.

NameTypeReqDescription
image_dir_pathstringOptional directory to write images into (referenced relatively from the HTML when output_path is given); images are omitted otherwise
input_pathstringyesPath to the .docx
output_pathstringOptional: write the HTML to this file (required if the result exceeds the inline limit)
overwritebooleanReplace output_path if it exists (default false)
update_tocbooleanRegenerate the document's table of contents entries before rendering (no page numbers in HTML; default false)
use_xsltbooleanUse the older XSLT-based exporter instead of the default visitor exporter (default false)

No output schema declared.

No examples provided.

convert_to_pdf ~186

Renders a Word document to PDF with docx4j's XSL-FO exporter (Apache FOP). Equations (OMML) are rendered (a very long single display equation will not line-wrap). Reports which fonts were substituted, so you can tell the user if the output may differ from Word.

NameTypeReqDescription
input_pathstringyesPath to the .docx
output_pathstringyesWhere to write the PDF
overwritebooleanReplace output_path if it exists (default false)
update_tocbooleanRegenerate the document's table of contents (entries and page numbers) before rendering, so it matches the output (default false; no effect if the document has no ToC)
use_xsltbooleanUse the older XSLT-based exporter instead of the default visitor exporter (default false)

No output schema declared.

No examples provided.

describe_template ~86

Inspects a Word template and reports what data it wants: for an OpenDoPE or content-control template, the skeleton XML to fill in (with the bound xpaths, repeats and conditions); for a mail-merge template, the MERGEFIELD names. Call this before fill_template.

NameTypeReqDescription
template_pathstringyesPath to the .docx template (inside an allowed root)

No output schema declared.

No examples provided.

docx_to_markdown ~185

Reads a Word document as Markdown (CommonMark + GFM): headings, lists, tables, footnotes and links are preserved as Markdown structure, and Word equations (OMML) become $..$ TeX math. Prefer this over extract_text when structure matters. Large results are truncated inline unless output_path is given.

NameTypeReqDescription
image_dir_pathstringOptional directory to extract images into (they are referenced from the Markdown); images are dropped otherwise
input_pathstringyesPath to the .docx
output_pathstringOptional: write the Markdown to this file (required if the result exceeds the inline limit)
overwritebooleanReplace output_path if it exists (default false)
tracked_changesstringHow to render tracked changes: accept them (default) or show insertions/deletions as markup

No output schema declared.

No examples provided.

extract_text ~112

Returns the plain text of a Word document's body, one line per paragraph or table, with no structure. For headings, tables and notes as Markdown use docx_to_markdown instead.

NameTypeReqDescription
input_pathstringyesPath to a .docx file, inside one of the server's allowed root directories
output_pathstringOptional: write the text to this file (required if the result exceeds the inline limit)
overwritebooleanReplace output_path if it exists (default false)

No output schema declared.

No examples provided.

fill_template ~252

Fills a Word template deterministically, preserving all its formatting. OpenDoPE and bound content-control templates take 'data' as an XML string (repeats and conditions are processed); mail-merge templates take 'data' as a JSON object of MERGEFIELD name to value. Use describe_template first to learn which, and what the data should look like.

NameTypeReqDescription
datastring|objectyesFor OpenDoPE / content-control templates: the filled-in XML document as a string (start from describe_template's skeleton_xml). For mail-merge templates: a JSON object mapping MERGEFIELD names to val…
headers_footersbooleanMail-merge mode: also merge fields in headers and footers (default true)
output_pathstringyesWhere to write the filled .docx
overwritebooleanReplace output_path if it exists (default false)
remove_sdtsbooleanXML mode: strip the content-control wrappers from the result (default true)
remove_xmlbooleanXML mode: drop the custom XML data part from the result (default true)
template_pathstringyesPath to the .docx template

No output schema declared.

No examples provided.

html_to_docx ~298

Creates a Word document from HTML using docx4j-ImportXHTML: headings, paragraphs, inline formatting, lists, tables, links and CSS become native Word markup, and <math> (MathML) becomes real, editable Word equations. Give a styles_template_path to inherit an organisation's styles (class names matching style names map to those styles). Remote images are not fetched; use data: URIs or local files under an allowed root.

NameTypeReqDescription
base_pathstringDirectory (inside an allowed root) against which relative image paths are resolved; defaults to input_path's directory. Remote (http/https) images are never fetched.
htmlstringThe HTML (loose HTML is fine; CSS in style attributes and <style> is honoured)
input_pathstringAlternatively, path to an .html file
modestringconvert (default): translate to native Word markup now. altchunk: embed the HTML for Word to convert when the file is opened (highest fidelity in Word, but docx4j cannot render it to PDF).
output_pathstringyesWhere to write the .docx
overwritebooleanReplace output_path if it exists (default false)
styles_template_pathstringOptional .docx whose styles, numbering, page setup and headers/footers the output should use; its body content is replaced

No output schema declared.

No examples provided.

markdown_to_docx ~207

Creates a properly styled Word document from Markdown: headings, lists and numbering, GFM tables, code, footnotes and task lists become native Word constructs (no HTML detour), and TeX math ($..$ / $$..$$) becomes real, editable Word equations (OMML) that also render in PDF/HTML export. Give a styles_template_path to inherit an organisation's styles. Remote images are not fetched.

NameTypeReqDescription
input_pathstringAlternatively, path to a .md file
markdownstringThe Markdown text (CommonMark + GFM tables, task lists, footnotes; $..$ TeX math)
output_pathstringyesWhere to write the .docx
overwritebooleanReplace output_path if it exists (default false)
styles_template_pathstringOptional .docx whose styles, numbering, page setup and headers/footers the output should use; its body content is replaced

No output schema declared.

No examples provided.

Common questions

What is the docx4j Word documents MCP server?

docx4j Word documents is an MCP server listed in the public MCP registry as io.github.plutext/docx4j-mcp. Read, convert and fill Word (.docx) documents: templates, Markdown/HTML in and out, PDF with math. This page covers its container image (ghcr.io/plutext/docx4j-mcp:0.2.0).

Is the docx4j Word documents MCP server safe to use?

docx4j Word documents scores 43 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the docx4j Word documents MCP server expose?

docx4j Word documents exposes 8 tools: describe_template, fill_template, convert_to_pdf, markdown_to_docx, docx_to_markdown, and 3 more. Their descriptions and schemas cost roughly 1,549 tokens of context every time the server is loaded.

Is the docx4j Word documents MCP server still maintained?

docx4j Word documents is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.