# Use cases Step-by-step scenarios for searching documents with AI agents over MCP: questions across a folder, quoting passages, keeping an index current, repository documents, email archives, and dates and amounts. Step-by-step scenarios for searching documents with AI agents over MCP — each page answers one real question completely, with the setup, the calls the agent makes, the results it gets back (captured from the server), and the exact prompt: * [How to search documents with AI agents using MCP]({{< ref "search/mcp/use-cases/search-documents-with-ai-agents.md" >}}) — start here: the index → search → quote pattern, which tool for which question, and the query language. * [How to ask questions across a folder of contracts with an AI agent]({{< ref "search/mcp/use-cases/search-a-folder-of-contracts.md" >}}) — which contracts say X, the clause that says it, and the unquoted-phrase trap. * [How to get the matching passages instead of reading whole files]({{< ref "search/mcp/use-cases/quote-matching-passages-not-whole-files.md" >}}) — grounded answers on a small context: fragments, the termsBefore/termsAfter dial, and variants. * [How to keep a document index current as files change]({{< ref "search/mcp/use-cases/keep-an-index-up-to-date.md" >}}) — one index per project, refreshed with one call — and what removal can and cannot do. * [How to let Claude Code or Cursor search the PDFs and Word documents in a repository]({{< ref "search/mcp/use-cases/search-project-documents-from-claude-code.md" >}}) — datasheets, specs and ADRs in PDF and DOCX — the files grep cannot read. * [How to search email archives and attachments with an AI agent, locally]({{< ref "search/mcp/use-cases/search-email-archives-locally.md" >}}) — PST, OST, MSG and EML — including the text of attached documents. * [How to find documents by date range, amount and file name with an AI agent]({{< ref "search/mcp/use-cases/find-documents-by-date-and-amount.md" >}}) — content: daterange(…), number ranges, file-name words — and the file-date trap. * [Running GroupDocs MCP servers on-premise: architecture and security model]({{< ref "search/mcp/use-cases/on-premise-document-search.md" >}}) — architecture and security model — what the index stores, and what travels to the model. New to the server? [Quick start]({{< ref "search/mcp/getting-started/_index.md" >}}) first.