Doc-Ops MCP
Doc-Ops MCP converts DOCX, Markdown, HTML and PDF between formats and stamps a watermark or QR code onto finished PDFs.
- 140 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The server reads and writes files at paths set by the agent.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/doc-ops-mcpDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The server reads and writes files at paths set by the agent.
This is third-party code. Review the repository files before installing.
What it does
Doc-Ops MCP reads and writes documents and converts them between formats: DOCX to PDF, HTML and Markdown, Markdown to PDF, HTML and DOCX, HTML to Markdown. For DOCX it parses OOXML to keep styles during conversion. Separate tools change content: batch text replacement, regular-expression replacement and heading-level edits. On PDFs the server adds a watermark from your own image or a default text one, plus a QR code. The `plan_conversion` tool picks a conversion path. Everything runs on npm packages, with no external system programs required.
Who it is for. Editors and developers who turn contracts, articles and reports from Markdown and DOCX into PDF and HTML straight from an agent chat.
Good fit when
- A contract in DOCX has to reach a client as a PDF with a logo watermark.
- An article sits in Markdown, while the site needs HTML.
- A company name or version has to be replaced across dozens of files.
- A finished PDF report should get a QR code with a link.
Not a fit when
- You need to edit a PDF as a layout: the server converts and stamps but does not change typesetting.
- Files cannot be handed to a third-party process on your machine.
- Pixel-exact pagination of complex tables is required, and conversion quality depends on the document.
Example request
Convert /Users/docs/report.docx to PDF and add the default watermark.MCP
- Transport
- stdio
- Authentication
- not required
Environment variables
`OUTPUT_DIR`- Folder where generated files are saved, `~/Documents` by default.
`CACHE_DIR`- Folder for temporary and cache files, `~/.cache/doc-ops-mcp` by default.
`WATERMARK_IMAGE`- Default watermark image path for PDF files.
`QR_CODE_IMAGE`- Default QR code image path for PDF files.
Limitations
The server reads and writes files on your machine: the output path comes from the `OUTPUT_DIR` variable, and an absolute `outputPath` bypasses it. Conversion from PDF to DOCX is not supported, and a watermark applies to PDFs only. For better PDF output the README suggests a separate `playwright-mcp`. Results depend on the source formatting, so check complex documents by eye. For deployment a Docker image is available.
How to disable. Remove the `doc-ops-mcp` entry from the MCP client configuration and clean the `OUTPUT_DIR` and `CACHE_DIR` directories.
FAQ
Which formats are supported?
PDF, DOCX, HTML and Markdown. DOCX goes to PDF, HTML and Markdown, and Markdown converts to all the others. The server does not convert from PDF to other formats.
Where are results saved?
In the `OUTPUT_DIR` directory, `~/Documents` by default. A relative `outputPath` resolves from it, while an absolute path is used as is.
How do I replace the watermark?
Point the `WATERMARK_IMAGE` variable at a PNG or JPG image. Without it a `doc-ops-mcp` text is stamped. The QR code comes from `QR_CODE_IMAGE` and is added only on request.
Which Node.js version is needed?
Version 18 or newer. System programs such as office suites are not needed.
Is there a Docker image?
Yes, a prebuilt image can be run and building from source. For a machine without Node.js this is handier than a global install.
Discussion
No questions or reviews yet.
Related
MCP serversMicrosoft's utility and MCP server that turn PDF, Word, Excel, PowerPoint, HTML and other files into Markdown for models
An MCP server that turns PDF, DOCX, XLSX, PPTX, images, audio, web pages and YouTube transcripts into Markdown
An MCP server on top of pandoc: the agent converts Markdown, HTML, DOCX, LaTeX, EPUB, ODT and other formats into one another
MCP PDF from ComPDF: the agent converts PDFs and images to Word, Excel, Markdown and JSON and merges, splits, protects and compares files via a cloud API
MCP Word server for docx editing with tracked changes: comments, footnotes, version comparison and a change log, all visible in Word
Docling is a CLI for mixed document archives, bringing PDFs, office files and spreadsheets into a shared format for AI search.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Doc-Ops MCP (this card) | no | not required | 140 | |
| MarkItDown | yes | not required | 194,189 | turns documents into Markdown; Doc-Ops MCP converts in several directions and stamps PDFs |
| mcp-pandoc | no | not required | 586 | a wrapper over the system pandoc; Doc-Ops MCP runs on npm packages with no external programs |
README in short
The server is built in pure JavaScript and speaks JSON-RPC 2.0. Clients connect it with a single configuration entry.