MarkItDown by pagespool is an MCP server published by com.pagespool, hosted at api.pagespool.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 1 tool, including convert_document.
Hosted MarkItDown: convert Word, PowerPoint, Excel, HTML and the text of PDFs to Markdown.
20 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Convert a document up to 8 MB to Markdown with MarkItDown and return it. Pass the file as base64 in `content_base64`, or as a download link in `file`, and its name in `filename`. The extension decides the type: .pdf, .docx, .pptx, .xlsx, .html, .htm or .txt. Returns `markdown` and `meta` (`filename`, `length` in characters). PDFs come back as the text of their text layer, without headings and without OCR. Works without an API key at the anonymous rate limit. Credits: 1 per call.
| Parameter | Type | Description |
|---|---|---|
| file | object | The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL. |
| filename * | string | The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read. |
| content_base64 | any | The file content, base64-encoded. Up to 8 MB before encoding. |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "convert_document",
"title": "Convert a document to Markdown with MarkItDown",
"description": "Convert a document up to 8 MB to Markdown with MarkItDown and return it.\n\nPass the file as base64 in `content_base64`, or as a download link in\n`file`, and its name in `filename`. The extension decides the type: .pdf,\n.docx, .pptx, .xlsx, .html, .htm or .txt. Returns `markdown` and `meta`\n(`filename`, `length` in characters). PDFs come back as the text of\ntheir text layer, without headings and without OCR. Works without an\nAPI key at the anonymous rate limit.\n\nCredits: 1 per call.",
"inputSchema": {
"type": "object",
"required": [
"filename"
],
"properties": {
"file": {
"type": "object",
"default": null,
"required": [
"download_url",
"file_id"
],
"properties": {
"file_id": {
"type": "string",
"description": "An identifier for the file. ChatGPT sets it; other clients may pass any label, such as the file name."
},
"file_name": {
"type": "string"
},
"mime_type": {
"type": "string"
},
"download_url": {
"type": "string",
"description": "A public https URL of the file."
}
},
"description": "The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL."
},
"filename": {
"type": "string",
"description": "The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read."
},
"content_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The file content, base64-encoded. Up to 8 MB before encoding."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"additionalProperties": true
},
"annotations": {
"title": "Convert a document to Markdown with MarkItDown",
"readOnlyHint": true,
"openWorldHint": true
}
}Hosted MarkItDown: convert Word, PowerPoint, Excel, HTML and the text of PDFs to Markdown.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.