Word .docx files to PDF
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Use this when the user uploads a Word .docx file and wants it as a PDF. Carries headings, paragraphs with alignment, bold, italic, underline, strikethrough, text sizes, links, bulleted and numbered lists with Word's numbers (decimal, letter and roman styles; other number styles print as digits and are listed as not carried), simple tables (merged cells, repeated header rows), JPEG and PNG images, page breaks, the page size and margins; footnotes and endnotes are printed at the end and tracked changes are accepted. Returns the PDF link, a read-back check of the PDF text, table cells, images and page size, and a list of each element type not carried (text boxes, shapes, charts, headers, footers, comments) with counts. Does not read .doc, password-protected or macro-enabled files, and does not keep fonts or colors. The link expires in about 1 hour.
The Word document to convert, e.g. report.docx (a .docx file up to 15 MB).
true (default) prints "page / total" centered at the bottom of each page; false prints no page numbers.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http word-to-pdf https://word-to-pdf.zovo.one/mcp
Use this when the user uploads a Word .docx file and wants it as a PDF. Carries headings, paragraphs with alignment, bold, italic, underline, strikethrough, text sizes, links, bulleted and numbered lists with Word's numbers (decimal, letter and roman styles; other number styles print as digits and are listed as not carried), simple tables (merged cells, repeated header rows), JPEG and PNG images, page breaks, the page size and margins; footnotes and endnotes are printed at the end and tracked changes are accepted. Returns the PDF link, a read-back check of the PDF text, table cells, images and page size, and a list of each element type not carried (text boxes, shapes, charts, headers, footers, comments) with counts. Does not read .doc, password-protected or macro-enabled files, and does not keep fonts or colors. The link expires in about 1 hour.
| Argument | Type | Description |
|---|---|---|
| file* | object | The Word document to convert, e.g. report.docx (a .docx file up to 15 MB). |
| page_numbers | boolean | true (default) prints "page / total" centered at the bottom of each page; false prints no page numbers. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"file"
],
"properties": {
"file": {
"type": "object",
"required": [
"download_url",
"file_id"
],
"properties": {
"file_id": {
"type": "string",
"description": "ChatGPT file id, e.g. file_abc123."
},
"file_name": {
"type": "string",
"description": "Original file name if known, e.g. statement.pdf."
},
"mime_type": {
"type": "string",
"description": "Media type if known, e.g. application/pdf."
},
"download_url": {
"type": "string",
"description": "Temporary download link for the file, supplied by ChatGPT."
}
},
"description": "The Word document to convert, e.g. report.docx (a .docx file up to 15 MB)."
},
"page_numbers": {
"type": "boolean",
"description": "true (default) prints \"page / total\" centered at the bottom of each page; false prints no page numbers."
}
}
}Use this when the user wants to know what a Word .docx file contains before converting it: counts of headings, paragraphs, list items, tables, cells, images, footnotes and sections, the page size and margins, and which element types would not be carried into a PDF (text boxes, shapes, charts, headers, footers, comments) with counts. Makes no PDF and does not edit the file.
| Argument | Type | Description |
|---|---|---|
| file* | object | The Word document to inspect, e.g. contract.docx (a .docx file up to 15 MB). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"file"
],
"properties": {
"file": {
"type": "object",
"required": [
"download_url",
"file_id"
],
"properties": {
"file_id": {
"type": "string",
"description": "ChatGPT file id, e.g. file_abc123."
},
"file_name": {
"type": "string",
"description": "Original file name if known, e.g. statement.pdf."
},
"mime_type": {
"type": "string",
"description": "Media type if known, e.g. application/pdf."
},
"download_url": {
"type": "string",
"description": "Temporary download link for the file, supplied by ChatGPT."
}
},
"description": "The Word document to inspect, e.g. contract.docx (a .docx file up to 15 MB)."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 8, 2026.