GroupDocs.Markdown MCP Server Leave feedback

GroupDocs.Markdown MCP server turns documents into clean, structured Markdown — PDF, Word, Excel, EPUB, MOBI, CHM and 20+ more formats — locally on your machine. It is the ingestion step for knowledge bases, RAG pipelines, and static sites, without uploading a single file.

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-markdown/markdown-net-mcp:latest

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

dnx GroupDocs.Markdown.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.

Three tools — a small surface, because the job is specific (full details in the tools reference):

• convert_to_markdown — the conversion, with control over images, page selection, dialect, and YAML front matter.
• get_document_info — format, page count, title, author, encryption flag, without converting.
• get_license_status — active licensing mode and metered consumption.

Ask in plain language — “turn this handbook into Markdown for the knowledge base” — and the agent does the rest.

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

Warning

Evaluation mode converts only the first three pages, with a watermark on each — and the resulting Markdown looks entirely valid. A knowledge base built from unlicensed conversions is almost empty and does not appear broken. Check get_license_status before an ingestion 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. Ingestion is exactly where documents usually leak: the corpus you are indexing is the corpus you cannot afford to upload. Details: On-premise architecture.

Both can produce Markdown. GroupDocs.Conversion is the general converter across 100+ formats in both directions. This server is specialised: dialect selection, image strategy, page ranges, and front matter are first-class parameters. If Markdown is the destination and you care how it looks, this is the one; if you need DOCX → XLSX → PDF as well, use Conversion.

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