GroupDocs.Watermark.Mcp

# GroupDocs.Watermark MCP Server

MCP server for GroupDocs.Watermark — add, search, and remove document watermarks via AI agents. Wraps GroupDocs.Watermark for .NET and exposes it as tool calls for Claude, Cursor, VS Code / GitHub Copilot, and other MCP-compatible clients. Supports PDF, DOCX, XLSX, PPTX, PNG, JPG, VSDX, and 50+ more document and image formats. Exposes AddWatermark, AddImageWatermark, SearchWatermarks, RemoveWatermarks, and GetDocumentInfo tools.

## Install

- With dnx (.NET 10 SDK, no install step): `dnx GroupDocs.Watermark.Mcp@26.9.0 --yes`
- As a global dotnet tool: `dotnet tool install -g GroupDocs.Watermark.Mcp` then run `groupdocs-watermark-mcp`
- As a Docker container: `docker run --rm -i -v $(pwd)/documents:/data ghcr.io/groupdocs-watermark/watermark-net-mcp:latest`
- Native prerequisite for native (dnx / global tool) runs on Linux and macOS: install libgdiplus — `sudo apt-get install -y libgdiplus libfontconfig1 ttf-mscorefonts-installer` on Linux, `brew install mono-libgdiplus` on macOS. Not needed on Windows (GDI+ built in) or in Docker (bundled in the image).

## MCP tools

- AddWatermark — add a text watermark (Arial, configurable font size + rotation) to a document and save the watermarked copy. Returns a saved-path message and download URL.
- AddImageWatermark — add an image watermark (logo, signature scan, stamp) to a document. Configurable opacity + rotation. Returns a saved-path message and download URL.
- SearchWatermarks — find existing watermarks (text + image) in a document and return their type, text, page, position, size, and rotation as JSON.
- RemoveWatermarks — remove existing watermarks from a document and save the cleaned copy. Optional text filter to scope removal to matching watermarks only.
- GetDocumentInfo — return file type, page count, size, and per-page dimensions of a document as JSON. Does not modify the document.

## Supported formats

PDF, DOCX, XLSX, PPTX, ODT, RTF, HTML, PNG, JPG, TIFF, BMP, GIF, MSG, EML, and 50+ other document and image formats.

## Environment variables

- GROUPDOCS_MCP_STORAGE_PATH — base folder for input + output (defaults to current working directory)
- GROUPDOCS_MCP_OUTPUT_PATH — optional, routes output files to a separate folder
- GROUPDOCS_LICENSE_PATH — path to GroupDocs.Total.lic, omit for evaluation mode (in evaluation mode the output document may include an additional evaluation watermark alongside the user-requested one)

## Licensing

The MCP server is MIT; the underlying GroupDocs.Watermark engine requires a license for production use. Evaluation mode (no license): The engine adds an extra evaluation watermark to processed output. A single server process can load at most 10 documents; further calls fail until the server restarts. Free 30-day temporary license: https://purchase.groupdocs.com/temporary-license/ — purchase: https://purchase.groupdocs.com/pricing/watermark/net

## Key links

- NuGet: https://www.nuget.org/packages/GroupDocs.Watermark.Mcp
- Repository: https://github.com/groupdocs-watermark/GroupDocs.Watermark.Mcp
- Docker: ghcr.io/groupdocs-watermark/watermark-net-mcp and docker.io/groupdocs/watermark-net-mcp
- License: MIT

## Example prompts for AI agents

- "Add a DRAFT watermark to report.pdf"
- "Stamp 'CONFIDENTIAL' as a watermark on contract.docx with 24-point font and -30 degree rotation"
- "What watermarks does invoice.pdf contain?"
- "Search slides.pptx for watermarks and tell me which pages have them"
- "List the watermarks in original.docx and final.docx — is anything different?"