PreteWorks API is an MCP server published by com.preteworks, hosted at api.preteworks.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 29 tools, including render_html_to_pdf, number_pdf, pdf_info, set_pdf_metadata, render_document.
One key for the document-to-web pipeline: scrape, AI-extract, build & edit PDFs, fill forms.
Nothing else in the archive shares these values.
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.
Render a full HTML document to a PDF. External subresources are blocked for safety — inline images/fonts as data: URIs. Returns a file_id (for chaining) and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| html * | string | The complete HTML document to render. |
{
"name": "render_html_to_pdf",
"title": "Render HTML to PDF",
"description": "Render a full HTML document to a PDF. External subresources are blocked for safety — inline images/fonts as data: URIs. Returns a file_id (for chaining) and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"description": "The complete HTML document to render."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Stamp a page number on every page. position: bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right. format supports {n} and {total}. Returns a file_id + ~1h URL.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
| start | number | First page's number (default 1). |
| format | string | e.g. '{n}' or '{n} / {total}' (default '{n}'). |
| position | string | Where to place it (default bottom-center). |
{
"name": "number_pdf",
"title": "Number PDF pages",
"description": "Stamp a page number on every page. position: bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right. format supports {n} and {total}. Returns a file_id + ~1h URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"start": {
"type": "number",
"description": "First page's number (default 1)."
},
"format": {
"type": "string",
"description": "e.g. '{n}' or '{n} / {total}' (default '{n}')."
},
"position": {
"type": "string",
"description": "Where to place it (default bottom-center)."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Read a PDF's metadata (title, author, subject, keywords, creator, producer, dates) plus page count and page size, as JSON.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
{
"name": "pdf_info",
"title": "Read PDF info",
"description": "Read a PDF's metadata (title, author, subject, keywords, creator, producer, dates) plus page count and page size, as JSON.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Set a PDF's title, author, subject, keywords (array or comma string) and/or creator. Only the fields you provide change. Returns a file_id + ~1h URL.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
| title | string | |
| author | string | |
| creator | string | |
| subject | string | |
| keywords | any |
{
"name": "set_pdf_metadata",
"title": "Set PDF metadata",
"description": "Set a PDF's title, author, subject, keywords (array or comma string) and/or creator. Only the fields you provide change. Returns a file_id + ~1h URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"title": {
"type": "string"
},
"author": {
"type": "string"
},
"creator": {
"type": "string"
},
"subject": {
"type": "string"
},
"keywords": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Render a structured document to a PDF from a named template (invoice, receipt, report). Money/totals are computed for you. Returns a file_id (for chaining) and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| data * | object | Template data. invoice/receipt: {seller:{name,address?,email?,logo_url?(data: URI)}, buyer?:{name,address?,email?}, number?, issued?/date?, due?, currency?, items:[{description,qty,unit_price}], tax_rate?, notes?, terms?}; receipt also takes amount_paid?, payment_method?. report: {title, subtitle?, … |
| template * | string | Document template. |
{
"name": "render_document",
"title": "Generate a document",
"description": "Render a structured document to a PDF from a named template (invoice, receipt, report). Money/totals are computed for you. Returns a file_id (for chaining) and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"template",
"data"
],
"properties": {
"data": {
"type": "object",
"description": "Template data. invoice/receipt: {seller:{name,address?,email?,logo_url?(data: URI)}, buyer?:{name,address?,email?}, number?, issued?/date?, due?, currency?, items:[{description,qty,unit_price}], tax_rate?, notes?, terms?}; receipt also takes amount_paid?, payment_method?. report: {title, subtitle?, author?, date?, sections:[{heading?,body?}]}. Money is computed server-side.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"template": {
"enum": [
"invoice",
"receipt",
"report"
],
"type": "string",
"description": "Document template."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Combine 2+ PDFs into a single PDF, in the order given. Inputs are file_ids (from prior tools) or base64 PDFs. Returns a file_id (for chaining) and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| pdfs * | array | 2+ PDF sources. Each: A file_id from a prior tool result, or a base64-encoded PDF. |
{
"name": "merge_pdfs",
"title": "Merge PDFs",
"description": "Combine 2+ PDFs into a single PDF, in the order given. Inputs are file_ids (from prior tools) or base64 PDFs. Returns a file_id (for chaining) and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdfs"
],
"properties": {
"pdfs": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 2,
"description": "2+ PDF sources. Each: A file_id from a prior tool result, or a base64-encoded PDF."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Keep only the specified pages of a PDF (e.g. [1,3,5]) and drop the rest, preserving order. Returns a file_id (for chaining) and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
| pages * | string | Pages to keep, e.g. '1,3,5-7'. |
{
"name": "select_pages",
"title": "Select PDF pages",
"description": "Keep only the specified pages of a PDF (e.g. [1,3,5]) and drop the rest, preserving order. Returns a file_id (for chaining) and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf",
"pages"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"pages": {
"type": "string",
"description": "Pages to keep, e.g. '1,3,5-7'."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Rotate every page of a PDF by 90, 180, or 270 degrees (clockwise). Returns a file_id (for chaining) and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
| degrees * | number | 90, 180, or 270. |
{
"name": "rotate_pdf",
"title": "Rotate PDF",
"description": "Rotate every page of a PDF by 90, 180, or 270 degrees (clockwise). Returns a file_id (for chaining) and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf",
"degrees"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"degrees": {
"type": "number",
"description": "90, 180, or 270."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Stamp a diagonal grey text watermark (e.g. "DRAFT", "CONFIDENTIAL") across every page of a PDF. Returns a file_id (for chaining) and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
| text * | string | The watermark text. |
{
"name": "watermark_pdf",
"title": "Watermark PDF",
"description": "Stamp a diagonal grey text watermark (e.g. \"DRAFT\", \"CONFIDENTIAL\") across every page of a PDF. Returns a file_id (for chaining) and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf",
"text"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"text": {
"type": "string",
"description": "The watermark text."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Extract the text content of a PDF — for RAG, summarization, or search. Accepts a file_id (from a prior tool) or a base64-encoded PDF, and returns the text inline. Not OCR: a scanned/image-only PDF returns little or no text.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
{
"name": "extract_pdf_text",
"title": "Extract text from a PDF",
"description": "Extract the text content of a PDF — for RAG, summarization, or search. Accepts a file_id (from a prior tool) or a base64-encoded PDF, and returns the text inline. Not OCR: a scanned/image-only PDF returns little or no text.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Combine PNG/JPEG images (base64) into a PDF, one image per page. Returns a file_id and a ~1h URL.
| Parameter | Type | Description |
|---|---|---|
| images * | array | Base64-encoded PNG/JPEG images, one per page (max 20). |
{
"name": "images_to_pdf",
"title": "Images to PDF",
"description": "Combine PNG/JPEG images (base64) into a PDF, one image per page. Returns a file_id and a ~1h URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"images"
],
"properties": {
"images": {
"type": "array",
"items": {
"type": "string"
},
"description": "Base64-encoded PNG/JPEG images, one per page (max 20)."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Render Markdown to a clean, print-styled PDF. Returns a file_id and a ~1h URL.
| Parameter | Type | Description |
|---|---|---|
| title | string | Document title. |
| markdown * | string | The Markdown to render. |
{
"name": "markdown_to_pdf",
"title": "Render Markdown to PDF",
"description": "Render Markdown to a clean, print-styled PDF. Returns a file_id and a ~1h URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"markdown"
],
"properties": {
"title": {
"type": "string",
"description": "Document title."
},
"markdown": {
"type": "string",
"description": "The Markdown to render."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Split a PDF into multiple PDFs — one per page by default, or by page ranges like '1-3;4-6'. Returns a file_id + URL per part.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
| ranges | string | e.g. '1-3;4-6'. Omit to split every page. |
{
"name": "split_pdf",
"title": "Split a PDF",
"description": "Split a PDF into multiple PDFs — one per page by default, or by page ranges like '1-3;4-6'. Returns a file_id + URL per part.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"ranges": {
"type": "string",
"description": "e.g. '1-3;4-6'. Omit to split every page."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}List a PDF's form fields (name, type, value, options) as JSON.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
{
"name": "read_pdf_form",
"title": "Read a PDF form",
"description": "List a PDF's form fields (name, type, value, options) as JSON.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Fill a PDF's form fields from a map of field -> value; optionally flatten. Returns a file_id and a ~1h URL.
| Parameter | Type | Description |
|---|---|---|
| pdf * | string | A file_id from a prior tool result, or a base64-encoded PDF. |
| fields * | object | Map of field name to value. |
| flatten | boolean | Flatten the form after filling (default false). |
{
"name": "fill_pdf_form",
"title": "Fill a PDF form",
"description": "Fill a PDF's form fields from a map of field -> value; optionally flatten. Returns a file_id and a ~1h URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf",
"fields"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"fields": {
"type": "object",
"description": "Map of field name to value.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"flatten": {
"type": "boolean",
"description": "Flatten the form after filling (default false)."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Convert a Word (.docx), Excel (.xlsx) or CSV file (base64) into clean Markdown — for RAG, agents and pipelines. DOCX keeps headings/lists/tables; spreadsheets become Markdown tables (one per sheet). Returns Markdown inline. Optional 'format' (docx|xlsx|csv) overrides auto-detection.
| Parameter | Type | Description |
|---|---|---|
| file * | string | Base64-encoded .docx, .xlsx or .csv file. |
| format | string | Optional format hint; auto-detected if omitted. |
{
"name": "file_to_markdown",
"title": "File to Markdown",
"description": "Convert a Word (.docx), Excel (.xlsx) or CSV file (base64) into clean Markdown — for RAG, agents and pipelines. DOCX keeps headings/lists/tables; spreadsheets become Markdown tables (one per sheet). Returns Markdown inline. Optional 'format' (docx|xlsx|csv) overrides auto-detection.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"file"
],
"properties": {
"file": {
"type": "string",
"description": "Base64-encoded .docx, .xlsx or .csv file."
},
"format": {
"enum": [
"docx",
"xlsx",
"csv"
],
"type": "string",
"description": "Optional format hint; auto-detected if omitted."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Turn rows of data into a downloadable XLSX (default) or CSV. 'rows' is an array of objects (keys → header row) or an array of arrays (first row is the header). Returns a file_id (for chaining) and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| rows * | array | Array of objects (keys→columns) or array of arrays (first row = header). |
| format | string | Output format (default xlsx). |
| sheet_name | string | Worksheet name (default 'Sheet1'). |
{
"name": "data_to_spreadsheet",
"title": "Create a spreadsheet from rows",
"description": "Turn rows of data into a downloadable XLSX (default) or CSV. 'rows' is an array of objects (keys → header row) or an array of arrays (first row is the header). Returns a file_id (for chaining) and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"rows"
],
"properties": {
"rows": {
"type": "array",
"items": {},
"minItems": 1,
"description": "Array of objects (keys→columns) or array of arrays (first row = header)."
},
"format": {
"enum": [
"xlsx",
"csv"
],
"type": "string",
"description": "Output format (default xlsx)."
},
"sheet_name": {
"type": "string",
"description": "Worksheet name (default 'Sheet1')."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Fetch up to 10 public URLs and return each as clean Markdown, in one call — for research/RAG over several pages at once. Private/internal hosts are blocked.
| Parameter | Type | Description |
|---|---|---|
| urls * | array | 1–10 http/https URLs. |
{
"name": "batch_scrape",
"title": "Batch: URLs to Markdown",
"description": "Fetch up to 10 public URLs and return each as clean Markdown, in one call — for research/RAG over several pages at once. Private/internal hosts are blocked.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"description": "1–10 http/https URLs."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Fetch a URL plus up to 7 more same-origin pages it links to (≤8 total), each as clean Markdown. Bounded and synchronous. Private/internal hosts are blocked.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The root http/https URL. |
| limit | integer | Max pages incl. root (default 5, max 8). |
{
"name": "crawl_site",
"title": "Crawl a site to Markdown",
"description": "Fetch a URL plus up to 7 more same-origin pages it links to (≤8 total), each as clean Markdown. Bounded and synchronous. Private/internal hosts are blocked.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The root http/https URL."
},
"limit": {
"type": "integer",
"maximum": 8,
"minimum": 1,
"description": "Max pages incl. root (default 5, max 8)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Discover the same-origin URLs linked from a page — the site map, with no page content fetched. Private/internal hosts are blocked.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The http/https URL to map. |
{
"name": "map_site",
"title": "Map a site's URLs",
"description": "Discover the same-origin URLs linked from a page — the site map, with no page content fetched. Private/internal hosts are blocked.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The http/https URL to map."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Extract specified fields from a web page, PDF, or Office file as JSON, using AI. Provide 'fields' plus ONE source: a 'url', a 'pdf' (file_id or base64), or a 'file' (base64 .docx/.xlsx/.csv). Returns a JSON object mapping each field to its value, or null when absent.
| Parameter | Type | Description |
|---|---|---|
| string | A file_id from a prior tool result, or a base64-encoded PDF. | |
| url | string | A public http/https URL to read. |
| file | string | A base64-encoded .docx, .xlsx or .csv file (converted to text first). |
| fields * | array | Field names to extract, e.g. ['invoice total','due date']. |
{
"name": "extract_data",
"title": "Extract structured data (AI)",
"description": "Extract specified fields from a web page, PDF, or Office file as JSON, using AI. Provide 'fields' plus ONE source: a 'url', a 'pdf' (file_id or base64), or a 'file' (base64 .docx/.xlsx/.csv). Returns a JSON object mapping each field to its value, or null when absent.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"fields"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool result, or a base64-encoded PDF."
},
"url": {
"type": "string",
"description": "A public http/https URL to read."
},
"file": {
"type": "string",
"description": "A base64-encoded .docx, .xlsx or .csv file (converted to text first)."
},
"fields": {
"type": "array",
"items": {
"type": "string"
},
"description": "Field names to extract, e.g. ['invoice total','due date']."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Summarize a web page, PDF, Office file (.docx/.xlsx/.csv), or raw text using AI. Provide ONE source: 'url', 'pdf' (file_id or base64), 'file' (base64), or 'text'. Optional 'max_words'. Returns the summary.
| Parameter | Type | Description |
|---|---|---|
| string | A file_id from a prior tool, or a base64-encoded PDF. | |
| url | string | A public http/https URL to read. |
| file | string | A base64-encoded .docx, .xlsx or .csv file. |
| text | string | Raw text to summarize directly. |
| max_words | integer | Approximate target length in words. |
{
"name": "summarize_document",
"title": "Summarize a document (AI)",
"description": "Summarize a web page, PDF, Office file (.docx/.xlsx/.csv), or raw text using AI. Provide ONE source: 'url', 'pdf' (file_id or base64), 'file' (base64), or 'text'. Optional 'max_words'. Returns the summary.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool, or a base64-encoded PDF."
},
"url": {
"type": "string",
"description": "A public http/https URL to read."
},
"file": {
"type": "string",
"description": "A base64-encoded .docx, .xlsx or .csv file."
},
"text": {
"type": "string",
"description": "Raw text to summarize directly."
},
"max_words": {
"type": "integer",
"maximum": 9007199254740991,
"description": "Approximate target length in words.",
"exclusiveMinimum": 0
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Answer a question grounded ONLY in a source document — a web page, PDF, Office file, or raw text. Provide 'question' plus ONE source: 'url', 'pdf', 'file' (base64), or 'text'. Says so when the answer isn't in the document.
| Parameter | Type | Description |
|---|---|---|
| string | A file_id from a prior tool, or a base64-encoded PDF. | |
| url | string | A public http/https URL to read. |
| file | string | A base64-encoded .docx, .xlsx or .csv file. |
| text | string | Raw text to answer from directly. |
| question * | string | The question to answer from the document. |
{
"name": "answer_from_document",
"title": "Answer a question from a document (AI)",
"description": "Answer a question grounded ONLY in a source document — a web page, PDF, Office file, or raw text. Provide 'question' plus ONE source: 'url', 'pdf', 'file' (base64), or 'text'. Says so when the answer isn't in the document.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"question"
],
"properties": {
"pdf": {
"type": "string",
"description": "A file_id from a prior tool, or a base64-encoded PDF."
},
"url": {
"type": "string",
"description": "A public http/https URL to read."
},
"file": {
"type": "string",
"description": "A base64-encoded .docx, .xlsx or .csv file."
},
"text": {
"type": "string",
"description": "Raw text to answer from directly."
},
"question": {
"type": "string",
"description": "The question to answer from the document."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Extract the text of a .docx document (base64). Returns the text inline.
| Parameter | Type | Description |
|---|---|---|
| docx * | string | Base64-encoded .docx file. |
{
"name": "docx_to_text",
"title": "DOCX to text",
"description": "Extract the text of a .docx document (base64). Returns the text inline.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"docx"
],
"properties": {
"docx": {
"type": "string",
"description": "Base64-encoded .docx file."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Convert a .docx document (base64) to a PDF. Returns a file_id and a ~1h URL.
| Parameter | Type | Description |
|---|---|---|
| docx * | string | Base64-encoded .docx file. |
{
"name": "docx_to_pdf",
"title": "DOCX to PDF",
"description": "Convert a .docx document (base64) to a PDF. Returns a file_id and a ~1h URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"docx"
],
"properties": {
"docx": {
"type": "string",
"description": "Base64-encoded .docx file."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Fetch a public http/https URL and return its main content as clean Markdown — ideal for giving an agent readable web content for research or RAG. Private/internal hosts are blocked.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The http/https URL to read. |
{
"name": "read_url",
"title": "Read a web page as Markdown",
"description": "Fetch a public http/https URL and return its main content as clean Markdown — ideal for giving an agent readable web content for research or RAG. Private/internal hosts are blocked.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The http/https URL to read."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Fetch a public http/https URL and render the live page to a PDF. Returns a file_id (chainable into the PDF tools) and a ~1h download URL. Private/internal hosts are blocked.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The http/https URL to snapshot. |
{
"name": "url_to_pdf",
"title": "Snapshot a web page as PDF",
"description": "Fetch a public http/https URL and render the live page to a PDF. Returns a file_id (chainable into the PDF tools) and a ~1h download URL. Private/internal hosts are blocked.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The http/https URL to snapshot."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}Fetch a public http/https URL and capture a PNG screenshot. Set full_page for the entire scroll height. Returns a file_id and a ~1h download URL.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The http/https URL to capture. |
| full_page | boolean | Capture the full scroll height (default: viewport). |
{
"name": "url_to_screenshot",
"title": "Screenshot a web page",
"description": "Fetch a public http/https URL and capture a PNG screenshot. Set full_page for the entire scroll height. Returns a file_id and a ~1h download URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The http/https URL to capture."
},
"full_page": {
"type": "boolean",
"description": "Capture the full scroll height (default: viewport)."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}Fetch a public http/https URL and return its rendered HTML, the links on the page, and page metadata (title/description/OpenGraph/canonical/favicon) — in one render. For clean Markdown use read_url instead. Private/internal hosts are blocked.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The http/https URL to scrape. |
| formats | array | Which representations to return (default: all three). |
{
"name": "scrape_page",
"title": "Scrape a web page (HTML + links + metadata)",
"description": "Fetch a public http/https URL and return its rendered HTML, the links on the page, and page metadata (title/description/OpenGraph/canonical/favicon) — in one render. For clean Markdown use read_url instead. Private/internal hosts are blocked.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The http/https URL to scrape."
},
"formats": {
"type": "array",
"items": {
"enum": [
"html",
"links",
"metadata"
],
"type": "string"
},
"description": "Which representations to return (default: all three)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}PreteWorks API — one metered key for the whole document-to-web pipeline; no install, nothing to host. Web: turn any public URL into clean Markdown (read_url), structured JSON via AI (extract_data), a PDF (url_to_pdf), or a screenshot (url_to_screenshot). PDF: create (from HTML, Markdown, images, .docx, or invoice/receipt/report templates), edit (merge, split, select/rotate/watermark/number pages, read/set metadata), and read (extract text, read/fill forms). Tools chain: most return a `file_id` you can pass as the input to another tool (e.g. url_to_pdf → watermark_pdf → extract_pdf_text) with no re-upload. Free tier: 500 units/month, no card; then pay per call. Every fetch is SSRF-guarded (private/internal hosts blocked).
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.