GroupDocs.Merger MCP Server Leave feedback

GroupDocs.Merger MCP server lets AI agents like Claude, Cursor, and Copilot merge documents and extract pages — PDF, Word, Excel, PowerPoint and 30+ more formats — locally on your machine. Nothing is uploaded to a web “merge PDF” service.

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-merger/merger-net-mcp:latest

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

dnx GroupDocs.Merger.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.

Four tools (full details in the tools reference):

• merge — combine two to four documents of the same format into one, in the order you give them.
• split — extract the pages you name, each saved as its own document.
• get_document_info — type, page count, size, per-page dimensions.
• get_license_status — active licensing mode and metered consumption.

Ask in plain language — “combine these three reports with the appendix last”, “pull out the signature page” — and the agent picks the tools.

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

Four documents per merge. One merge call takes file1–file4. For more, merge in rounds and chain each result into the next call — an agent will do the bookkeeping if you ask.

Same format family. All PDFs, or all DOCX. Mixing a Word file into a set of PDFs has no defined result; convert first with the GroupDocs.Conversion MCP server, then merge.

Warning

Evaluation mode trims the result to three pages and stamps a trial badge on each one — silently. A merge of four long PDFs comes back as three pages and looks like it worked. Check get_license_status before a real run; see Licensing.

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.

The web is full of “merge PDF” pages, and every one of them asks you to upload the document. Choose this server when you need: the merge to happen on your machine; the same model across 30+ formats, not just PDF; format-preserving merges rather than flattened output; merging and splitting inside an agent workflow rather than by hand; 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: Merger forum