GroupDocs.Signature MCP Server Leave feedback

GroupDocs.Signature MCP server lets AI agents like Claude, Cursor, and Copilot sign documents, verify signatures, and read the codes inside them — PDF, Word, Excel, PowerPoint and 30+ more formats — locally on your machine. Documents stay put; so do your signing certificates.

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-signature/signature-net-mcp:latest

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

dnx GroupDocs.Signature.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.

Nine tools in three groups (full details in the tools reference):

Sign — sign applies a text, qrcode, barcode, or digital signature and saves a signed copy.

Check — verify answers “is this signed and still valid?”; search_digital_signatures returns signer, issuer, serial number, validity window, and timestamp.

Read — search_qr_codes and search_barcodes decode machine-readable codes; search_text_signatures and search_image_signatures find stamps, labels, and seals.

Ask in plain language — “sign this with a QR code holding the order number”, “who signed this and is it still valid?” — and the agent picks the tools.

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

This is the distinction to get right before automating anything:

Both are useful; only the second one survives a dispute. And because visual marks change the file’s bytes, applying one after a digital signature invalidates it — sign digitally last.

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. For signing that property is not a nicety: your certificate file and its password are read locally and never transmitted. Details: On-premise architecture.

A PDF tool signs PDFs, one at a time, by hand. Choose this server when you need: the same signing and verification model across 30+ formats; signatures an agent can apply and check inside a workflow rather than in a UI; QR and barcode data extraction from the documents you already handle; certificate details as structured data for an audit trail; 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: Signature forum