Skip to content

Commit de9b5f8

Browse files
author
Vsevolod Orefin
committed
Merge remote-tracking branch 'origin/master'
2 parents 3bdf377 + cd0c753 commit de9b5f8

33 files changed

Lines changed: 494 additions & 229 deletions

‎mcp/use-cases/batch-convert-folder.md‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -68,6 +68,7 @@ The prompt is the orchestration layer: filtering ("only the 2025 ones"), sequenc
6868
* **Existing files are never overwritten** — re-running a batch produces distinctly-named files rather than clobbering earlier output.
6969
* **Large batches:** agents typically process files sequentially; a few hundred documents work fine, and the report at the end tells you exactly what happened. For scheduled/unattended pipelines beyond agent sessions, the same engine is scriptable via the [.NET library]({{< ref "conversion/net/_index.md" >}}).
7070
* **Evaluation mode** caps a single server process at 15 opened documents — a [license]({{< ref "conversion/mcp/getting-started/licensing.md" >}}) lifts this for real batches.
71+
* **Failures are reported per file.** When a file cannot be converted — an unsupported source format or a wrong password — the response for that file starts with the operation and the reason, and [`convert`]({{< ref "conversion/mcp/tools-reference/convert.md" >}}) accepts an optional `password`. Put "list any file that failed" in the prompt so a failure does not pass unnoticed.
7172

7273
## FAQ
7374

@@ -79,3 +80,7 @@ They are kept by default — conversion writes new files. A separate output fold
7980

8081
**Can I filter which files get converted?**
8182
Say it in the prompt — by extension, name pattern, or even content questions the agent checks via [`get_document_info`]({{< ref "conversion/mcp/tools-reference/get-document-info.md" >}}).
83+
84+
## Read more
85+
86+
* [A whole folder, one prompt: batch conversion with Claude and MCP](https://blog.groupdocs.com/conversion/batch-convert-folder-ai-agent-mcp/) — the same scenario on the GroupDocs blog, with worked examples and the trade-offs.

‎mcp/use-cases/convert-documents-with-ai-agents.md‎

Lines changed: 11 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -68,7 +68,7 @@ Restart the client. Documents go in the storage folder; conversions come back th
6868

6969
**PDF → DOCX** (make a PDF editable):
7070

71-
> Convert scan-agreement.pdf to DOCX so I can edit it
71+
> Convert agreement.pdf to DOCX so I can edit it
7272
7373
**DOCX → PDF** (finalize for distribution):
7474

@@ -94,3 +94,13 @@ No. The server runs locally over stdio; the data path is agent → local server
9494

9595
**Which AI clients work?**
9696
Claude Desktop, Claude Code, VS Code / GitHub Copilot, Visual Studio 2022, Cursor, Windsurf, Cline, Codex CLI, JetBrains Rider — [setup for each]({{< ref "conversion/net/mcp/install-in-ai-clients.md" >}}).
97+
98+
**Can it make a scanned PDF editable?**
99+
Only if the PDF has a text layer. OCR is not part of this server, so an image-only scan will not come out as editable text.
100+
101+
**What happens without a license?**
102+
The server runs in evaluation mode: converted output carries an evaluation watermark, and one server process opens at most 15 documents. Ask *"what is the license status of the conversion server?"* first — see [Licensing]({{< ref "conversion/mcp/getting-started/licensing.md" >}}).
103+
104+
## Read more
105+
106+
* [Why your AI agent should not convert documents by itself](https://blog.groupdocs.com/conversion/ai-agents-convert-documents-properly-mcp/) — the same scenario on the GroupDocs blog, with worked examples and the trade-offs.

‎mcp/use-cases/convert-pdf-to-markdown.md‎

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -75,14 +75,19 @@ The same one-prompt pattern converts DOCX, XLSX, PPTX, HTML, and the rest of the
7575

7676
* **Output missing structure?** Scanned (image-only) PDFs have no text layer to convert — OCR is not currently part of this server; see the OCR question in [Troubleshooting & FAQ]({{< ref "conversion/mcp/troubleshooting-faq.md" >}}).
7777
* **Server not visible in the client?** Restart the client after registration; see [Troubleshooting]({{< ref "conversion/mcp/troubleshooting-faq.md" >}}).
78+
* **Watermark on the output, or calls failing after 15 documents?** That is evaluation mode; check with [`get_license_status`]({{< ref "conversion/mcp/tools-reference/get-license-status.md" >}}) and see [Licensing]({{< ref "conversion/mcp/getting-started/licensing.md" >}}).
7879

7980
## FAQ
8081

8182
**Does PDF to Markdown work offline?**
82-
Yes — after the one-time package/image download, conversion runs fully locally; no network is used at runtime.
83+
Yes — after the one-time package/image download, conversion runs fully locally with a license file or in evaluation mode. Metered licensing reports usage (never document content) to GroupDocs, so it needs outbound access — see [Licensing]({{< ref "conversion/mcp/getting-started/licensing.md" >}}).
8384

8485
**Are tables preserved in the Markdown?**
8586
Yes, as Markdown pipe tables; complex layouts are where the commercial engine earns its keep versus basic extractors.
8687

8788
**Can I convert Markdown back to PDF or Word?**
8889
Yes — [Export Markdown to PDF or Word]({{< ref "conversion/mcp/use-cases/export-markdown-to-pdf-word.md" >}}).
90+
91+
## Read more
92+
93+
* [3 ways to turn PDFs into LLM-ready Markdown (and why local wins)](https://blog.groupdocs.com/conversion/pdf-to-llm-ready-markdown-locally-mcp/) — the same scenario on the GroupDocs blog, with worked examples and the trade-offs.

‎mcp/use-cases/export-markdown-to-pdf-word.md‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -70,3 +70,10 @@ Yes — native, editable DOCX with proper styles for headings, lists, and tables
7070

7171
**What about Markdown to other formats?**
7272
Markdown converts to the same target set as other inputs — HTML, PNG, and more; see [supported formats]({{< ref "conversion/mcp/supported-formats.md" >}}).
73+
74+
**Will the exported PDF carry a watermark?**
75+
Only in evaluation mode: unlicensed output carries an evaluation watermark, so apply a license before you deliver reports outside the team — see [Licensing]({{< ref "conversion/mcp/getting-started/licensing.md" >}}).
76+
77+
## Read more
78+
79+
* [Automate report delivery: let the agent write Markdown and ship Word](https://blog.groupdocs.com/conversion/export-ai-markdown-to-pdf-word-mcp/) — the same scenario on the GroupDocs blog, with worked examples and the trade-offs.

‎mcp/use-cases/on-premise-document-conversion.md‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -84,3 +84,7 @@ No. Stdio only; it is a child process of your AI client (or of your agent runtim
8484

8585
**How do updates work in a restricted network?**
8686
Pull the pinned image version in a controlled window, re-tag internally, and roll it out like any other container update.
87+
88+
## Read more
89+
90+
* [3 architectures for AI document processing, and the one that keeps files inside your network](https://blog.groupdocs.com/total/on-premise-ai-document-processing-mcp/) — the same scenario on the GroupDocs blog, with worked examples and the trade-offs.

‎net/_includes/supported-conversions/cad.md‎

Lines changed: 3 additions & 3 deletions
Large diffs are not rendered by default.

‎net/_includes/supported-conversions/compression.md‎

Lines changed: 23 additions & 23 deletions
Large diffs are not rendered by default.

‎net/_includes/supported-conversions/diagram.md‎

Lines changed: 12 additions & 12 deletions
Large diffs are not rendered by default.

0 commit comments

Comments
 (0)