Tools / doc.convert
Document to Markdown
doc.convert
Word, Excel, PowerPoint, EPUB and CSV files as Markdown, from a URL or base64, up to 10 MB.
MediaLater set3 units per callnot cachedMCP: doc_convertv1.0.0
When to use it
Use to read an office document you cannot open yourself: a .docx report, an .xlsx or .csv table, a .pptx deck or an .epub book. Headings, lists and tables are kept; images are dropped. For PDFs use pdf.extract, for web pages use web.markdown.
Input
| Field | Type | Description |
|---|---|---|
url | string (≤ 2048 chars) | Absolute http or https URL of the file. Use instead of base64. |
base64 | string (≤ 14000000 chars) | Base64-encoded file bytes, up to 10 MB once decoded. Use instead of url. |
format | one of auto, docx, xlsx, pptx, epub, csv | File type. auto detects it from the file itself. Default: "auto". |
sheet | string (≤ 100 chars) | xlsx only: one sheet, by name or by number starting at 1. Leave out for every sheet. |
max_rows | integer (≥ 1, ≤ 2000) | xlsx and csv: rows to read from the top of each sheet. Default: 200. |
max_chars | integer (≥ 1000, ≤ 300000) | Length limit of the Markdown. Default: 100000. |
Output
Returns data with: format, title, markdown, chars, truncated, sheets: [{name, rows, truncated}] (xlsx only).
Request
curl -X POST https://agentops.tools/v1/doc.convert \
-H 'content-type: application/json' \
-d '{"url":"https://agentops.tools/samples/report.docx"}'Over MCP the tool is named doc_convert. Over A2A its skill id is doc.convert. Same input, same envelope.
Try it
Counts against your rate limit.
Sources
Notes
- Spreadsheet cells show their last saved values; formulas are not recalculated.
- Older binary files (.doc, .xls, .ppt) are not supported; save them as .docx, .xlsx or .pptx first.