Content is loading…
Convert a DOCX or XLSX file URL to clean Markdown with headings and tables.
office_to_markdown#docx#xlsx#word#excel#markdownDownloads and converts .docx or .xlsx files from a URL into structured Markdown. Accepts url, format (docx/xlsx), sheet name, and maxRows (default 500) to return formatted text, tables, and headers. Output is capped at 400KB and input files must be under 10MB.
| Name | Type | Required | Description |
|---|---|---|---|
url | string | required | URL of a .docx or .xlsx file (max 10MB) |
format | enum ("docx" | "xlsx") | optional | File type. Default: inferred from the URL extension / Content-Type. |
sheet | string | optional | XLSX only: sheet name to convert. Default: all sheets. |
maxRows | number | optional | XLSX only: cap rows per sheet in the output. Default 500. |
{
"url": "https://example.com/quarterly-report.docx"
}{
"url": "https://example.com/budget.xlsx",
"sheet": "Q3",
"maxRows": 100
}curl -X POST https://toolsy.my/api/mcp \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "office_to_markdown",
"arguments": {
"url": "https://example.com/quarterly-report.docx"
}
}
}'Extract text from any PDF URL page by page, with document metadata.
pdf_extract_textFetch any public URL and return its body, optionally as Markdown.
fetch_urlExtract clean article text from any URL using Mozilla Readability.
extract_text_from_urlGenerate a free API key or set up an OAuth connector for Claude.ai.