GroupDocs.Watermark MCP Server Leave feedback

GroupDocs.Watermark MCP server lets AI agents like Claude, Cursor, and Copilot add, find, and remove watermarks in documents and images — PDF, Word, Excel, PowerPoint, images and 50+ more formats — locally on your machine.

Run it with one command. The Docker image is self-contained — the runtime and every native dependency the engine needs are inside it:

docker run --rm -i -v $(pwd)/documents:/data \
  ghcr.io/groupdocs-watermark/watermark-net-mcp:latest

With the .NET 10 SDK installed, the same server also runs without Docker:

dnx GroupDocs.Watermark.Mcp --yes

Both are the .NET build of the server and run on Windows, Linux, and macOS. Other platforms will each get their own launcher — see Install for your platform.

Or use the guided installer to register the server in your AI client, verify the setup, and configure shared folders in one pass.

Six tools (full details in the tools reference):

• add_watermark — a text watermark with font size and rotation.
• add_image_watermark — a logo, stamp, or scanned signature, with opacity.
• search_watermarks — what a document already carries.
• remove_watermarks — all of them, or only those matching a text filter.
• get_document_info — type, pages, structure.
• get_license_status — active licensing mode and metered consumption.

Ask in plain language — “stamp DRAFT across this deck”, “take the old watermark off these” — and the agent picks the tools.

Installation, prerequisites, and client configuration are platform-specific; the tools and licensing model below are the same everywhere.

Worth being clear, because agents will do exactly what you ask: a watermark makes provenance visible and casual reuse awkward. It does not prevent copying, does not protect the text underneath, and can be removed by someone who wants to. If you need the document to be unreadable to the wrong people, control access; to be tamper-evident, use a digital signature; to have content permanently gone, use redaction.

Exact config blocks for every client: Register in AI clients.

The server uses MCP’s local stdio transport: your AI client starts the server as a child process and talks to it over standard input/output. No inbound ports, no external endpoints, no telemetry — the data path is agent → local server → local filesystem. Details: On-premise architecture.

Office and PDF tools can stamp their own format, by hand. Choose this server when you need: one model across 50+ formats including images; watermarks as objects you can later find and remove, not pixels baked into a page; batch marking driven from a prompt; image watermarks with opacity control; and the fidelity of the commercial GroupDocs engine trusted by enterprise teams for over a decade.

• Quick start · Use cases · Troubleshooting & FAQ
• GitHub: server source · installer · integration tests
• NuGet package · Docker image · MCP Registry
• Questions: Watermark forum