# Use cases Step-by-step scenarios for working with document metadata through AI agents over MCP: auditing what files carry, stripping metadata before sharing, correcting properties in bulk, and reading EXIF from images. Step-by-step scenarios for reading, correcting, and removing metadata with AI agents over MCP — each page answers one real question completely, with the config, the exact prompt, and the expected result: * [How to audit document metadata with an AI agent]({{< ref "metadata/mcp/use-cases/audit-document-metadata.md" >}}) — start here: what your files are carrying, and how to ask precisely. * [How to strip metadata from documents before sharing them]({{< ref "metadata/mcp/use-cases/strip-metadata-before-sharing.md" >}}) — the cleanup pass — what it removes, what it cannot, and which file to send. * [How to correct document properties in bulk with an AI agent]({{< ref "metadata/mcp/use-cases/bulk-edit-document-properties.md" >}}) — one prompt, many files — and the chaining rule that keeps every edit. * [How to read EXIF, XMP, and IPTC data from images with AI]({{< ref "metadata/mcp/use-cases/read-exif-from-images.md" >}}) — cameras, timestamps, GPS — and the evaluation limit that hides the GPS. * [Running GroupDocs MCP servers on-premise: architecture and security model]({{< ref "metadata/mcp/use-cases/on-premise-metadata-processing.md" >}}) — architecture and security model for regulated environments. New to the server? [Quick start]({{< ref "metadata/mcp/getting-started/_index.md" >}}) first.