Htmlpdf Transform Mcp is an MCP server published by io.github.varvararatta, hosted at htmlpdf-transform-mcp.mcpize.run. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 5 tools, including html_to_markdown, html_to_text, extract_tables_from_html, json_to_markdown_table, health_check.
Htmlpdf Transform Mcp connects AI agents to real public APIs via MCP. Tools include
298 connections through 5 shared values. Tap any node.
Convert HTML to clean Markdown. Returns: {markdown, original_length, markdown_length}
| Parameter | Type | Description |
|---|---|---|
| html * | string |
{
"name": "html_to_markdown",
"description": "Convert HTML to clean Markdown.\n Returns: {markdown, original_length, markdown_length}",
"inputSchema": {
"type": "object",
"title": "html_to_markdownArguments",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"title": "Html"
}
}
}
}Strip all HTML tags and return clean plain text. Returns: {text, word_count}
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.
Inferred from the host name and headers: what a server runs on, not who runs it.
| Parameter | Type | Description |
|---|---|---|
| html * | string |
{
"name": "html_to_text",
"description": "Strip all HTML tags and return clean plain text.\n Returns: {text, word_count}",
"inputSchema": {
"type": "object",
"title": "html_to_textArguments",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"title": "Html"
}
}
}
}Extract all tables from HTML as structured data. Returns: {tables: [{headers, rows, row_count}]}
| Parameter | Type | Description |
|---|---|---|
| html * | string |
{
"name": "extract_tables_from_html",
"description": "Extract all tables from HTML as structured data.\n Returns: {tables: [{headers, rows, row_count}]}",
"inputSchema": {
"type": "object",
"title": "extract_tables_from_htmlArguments",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"title": "Html"
}
}
}
}Convert list of dicts or list of lists to Markdown table. Returns: {table, rows, columns}
| Parameter | Type | Description |
|---|---|---|
| data * | array | |
| headers | any |
{
"name": "json_to_markdown_table",
"description": "Convert list of dicts or list of lists to Markdown table.\n Returns: {table, rows, columns}",
"inputSchema": {
"type": "object",
"title": "json_to_markdown_tableArguments",
"required": [
"data"
],
"properties": {
"data": {
"type": "array",
"items": {},
"title": "Data"
},
"headers": {
"anyOf": [
{
"type": "array",
"items": {}
},
{
"type": "null"
}
],
"title": "Headers",
"default": null
}
}
}
}Server health check.
No parameters.
{
"name": "health_check",
"description": "Server health check.",
"inputSchema": {
"type": "object",
"title": "health_checkArguments",
"properties": {}
}
}HTML/text transformation — pure Python, zero auth, zero APIs
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.