# Use cases Step-by-step scenarios for letting AI agents see documents over MCP: page previews, inspecting before rendering, reading charts and scans, and keeping it all local. Step-by-step scenarios for rendering document pages with AI agents over MCP — each page answers one real question completely, with the exact prompt and the expected result: * [How to let an AI agent see document pages]({{< ref "viewer/mcp/use-cases/preview-documents-with-ai-agents.md" >}}) — start here: inspect, render, and read a page — the pattern every scenario uses. * [How to check a document's pages before rendering them]({{< ref "viewer/mcp/use-cases/inspect-a-document-before-rendering.md" >}}) — page count, page size, and protected files — before any image is made. * [How to have an AI agent read charts, diagrams, and scanned pages]({{< ref "viewer/mcp/use-cases/read-charts-and-scanned-pages.md" >}}) — the content that text extraction misses, read from the page image. * [How to create page images of documents for reports and tickets]({{< ref "viewer/mcp/use-cases/page-images-for-reports-and-tickets.md" >}}) — saved PNGs of the pages that matter, named predictably. * [Running GroupDocs MCP servers on-premise: architecture and security model]({{< ref "viewer/mcp/use-cases/on-premise-document-viewing.md" >}}) — architecture and security model for regulated environments — the page to send your security reviewer. New to the server? [Quick start]({{< ref "viewer/mcp/getting-started/_index.md" >}}) first.