Agent Data Tools: Documents to text
5 tools: PDF, Word, Excel, PowerPoint and web pages to Markdown; invoice fields as JSON.
Should I use this
Quality & Safety
Findings (5)
- HIGH
- MEDIUMin extract
- MEDIUMin extract_rendered
- MEDIUMin pdf_text
- MEDIUMin document_text
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"agent-data-tools-documents": {
"url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/documents"
}
}
}Remote endpoints
https://agent-data-tools.revmesh2074.workers.dev/mcp/documentsstreamable-httpWhat it can do
Tool inventory
Tools (5)
🟢extract(url, maxChars, format, section)
Fetch any public web page URL and get clean, LLM-ready text or Markdown: main content, code blocks, tables, links and headings, for RAG and agent context. Static HTML, Markdown or text; optional section ID. Default 20,000 output characters, max 100,000; input 2 MiB. No JavaScript rendering (see /extract/rendered), logins or paywalls. Empty pages, bad sections, browser challenges and errors are not charged. Use to read docs or articles. Example: url=https://example.com. Price $0.002/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute http(s) URL of the page to fetch"
},
"maxChars": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "Maximum characters of body text to return (500-100000, default 20000)"
},
"format": {
"type": "string",
"enum": [
"text",
"markdown",
"both"
],
"description": "Returned representation: text (default), markdown, or both. HTML structured details are included in every format; Markdown/plain sources have empty details."
},
"section": {
"type": "string",
"description": "Optional exact visible HTML ID within primary content, 1-500 characters. Heading scope includes subsections until next same/higher-level heading; section/article/main/div scope is its subtree. Missing/ambiguous/unsupported targets fail uncharged. URL fragments alone do not select a section. Leave it out to read the whole page."
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}Output Schema
{
"type": "object",
"properties": {
"url": {
"type": "string"
},
"finalUrl": {
"type": "string"
},
"status": {
"type": "integer"
},
"contentType": {
"type": "string"
},
"sourceMetadata": {
"type": "object",
"required": [
"verification",
"authors",
"dates",
"truncated"
],
"description": "Page-level source declarations, not verified authorship or freshness. Head author/Open Graph date tags and bounded direct Schema.org JSON-LD Article/WebPage-like nodes only; exact-URL matches preferred, otherwise only one identity-free candidate. Author @id references resolve only to unambiguous local Person/Organization names, with both paths recorded. No external context/reference fetching or general JSON-LD expansion. Separate 2000-character value+provenance budget; 5 authors/10 dates. Original date strings are not normalized. Empty for Markdown/plain sources; unrelated entities and ambiguous nodes are omitted with warnings.",
"properties": {
"verification": {
"const": "not_verified"
},
"truncated": {
"type": "boolean"
},
"authors": {
"type": "array",
"maxItems": 5,
"items": {
"type": "object",
"required": [
"value",
"source"
],
"properties": {
"value": {
"type": "string",
"maxLength": 256
},
"source": {
"type": "string",
"maxLength": 256
}
}
}
},
"dates": {
"type": "array",
"maxItems": 10,
"items": {
"type": "object",
"required": [
"value",
"source",
"kind"
],
"properties": {
"value": {
"type": "string",
"maxLength": 128
},
"source": {
"type": "string",
"maxLength": 256
},
"kind": {
"enum": [
"published",
"modified"
]
}
}
}
}
}
},
"linkBaseUrl": {
"type": "string",
"description": "Effective source-derived HTTP(S) base for links: the first supported HTML base href outside inert/foreign subtrees, otherwise finalUrl. Credentials and non-HTTP(S) base values are ignored with a warning. HTML links/canonical use this base; raw Markdown keeps relative syntax and can be resolved using this field. No linked resource is fetched. This static interpretation does not evaluate scripts or Content Security Policy."
},
"sourceFormat": {
"enum": [
"html",
"markdown",
"plain"
],
"description": "Source interpretation. Markdown is identified by text/markdown, or a .md/.markdown final path served as text/plain (warned). Markdown syntax is retained verbatim within the cap, not converted to HTML or parsed for structured details; text also retains that syntax. HTML section IDs are unsupported for Markdown/plain text."
},
"title": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"lang": {
"type": [
"string",
"null"
]
},
"canonical": {
"type": [
"string",
"null"
]
},
"format": {
"enum": [
"text",
"markdown",
"both"
]
},
"text": {
"type": "string",
"maxLength": 100000
},
"markdown": {
"type": "string",
"maxLength": 100000
},
"textLength": {
"type": "integer",
"minimum": 0,
"description": "Full extracted text length before the character cap, within the input limit."
},
"truncated": {
"type": "boolean",
"description": "Input or requested primary representation is incomplete. Structured detail limits are reported separately in warnings."
},
"contentSelection": {
"enum": [
"main",
"article",
"body",
"plain"
]
},
"contentHash": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"hashFormat": {
"enum": [
"text",
"markdown"
]
},
"fetchedAt": {
"type": "string"
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"headings": {
"type": "array",
"maxItems": 100,
"items": {
"type": "object",
"required": [
"level",
"text",
"id"
],
"properties": {
"level": {
"type": "integer",
"minimum": 1,
"maximum": 6
},
"text": {
"type": "string"
},
"id": {
"type": [
"string",
"null"
],
"maxLength": 500,
"description": "Source HTML heading ID or direct child anchor ID, when present and supported; not a generated slug."
}
}
}
},
"section": {
"description": "Null for full primary-content reading. Otherwise the explicitly requested scope; title/description/canonical remain page-level metadata. Heading scope ends before the next same/higher-level heading, including nested subsections; container scope is its subtree.",
"anyOf": [
{
"type": "null"
},
{
"type": "object",
"required": [
"id",
"title",
"kind",
"headingLevel"
],
"properties": {
"id": {
"type": "string",
"maxLength": 500
},
"title": {
"type": [
"string",
"null"
]
},
"kind": {
"enum": [
"heading",
"container"
]
},
"headingLevel": {
"type": [
"integer",
"null"
],
"minimum": 1,
"maximum": 6
}
}
}
]
},
"links": {
"type": "array",
"maxItems": 200,
"items": {
"type": "object",
"required": [
"href",
"text"
],
"properties": {
"href": {
"type": "string"
},
"text": {
"type": "string"
}
}
}
},
"codeBlocks": {
"type": "array",
"maxItems": 20,
"items": {
"type": "object",
"required": [
"language",
"text",
"truncated"
],
"properties": {
"language": {
"type": [
"string",
"null"
]
},
"text": {
"type": "string",
"maxLength": 20000
},
"truncated": {
"type": "boolean"
}
}
}
},
"tables": {
"type": "array",
"maxItems": 20,
"items": {
"type": "object",
"required": [
"caption",
"rows",
"headerRows",
"hasSpans",
"truncated"
],
"properties": {
"caption": {
"type": [
"string",
"null"
]
},
"rows": {
"type": "array",
"maxItems": 100,
"items": {
"type": "array",
"maxItems": 20,
"items": {
"type": "string"
}
}
},
"headerRows": {
"type": "array",
"items": {
"type": "integer",
"minimum": 0,
"maximum": 99
}
},
"hasSpans": {
"type": "boolean"
},
"truncated": {
"type": "boolean"
}
}
}
}
},
"required": [
"url",
"finalUrl",
"status",
"contentType",
"sourceFormat",
"linkBaseUrl",
"sourceMetadata",
"title",
"description",
"lang",
"canonical",
"headings",
"section",
"links",
"codeBlocks",
"tables",
"contentSelection",
"warnings",
"format",
"textLength",
"truncated",
"contentHash",
"hashFormat",
"fetchedAt"
],
"oneOf": [
{
"properties": {
"format": {
"const": "text"
},
"hashFormat": {
"const": "text"
}
},
"required": [
"text"
],
"not": {
"required": [
"markdown"
]
}
},
{
"properties": {
"format": {
"const": "markdown"
},
"hashFormat": {
"const": "markdown"
}
},
"required": [
"markdown"
],
"not": {
"required": [
"text"
]
}
},
{
"properties": {
"format": {
"const": "both"
},
"hashFormat": {
"const": "text"
}
},
"required": [
"text",
"markdown"
]
}
]
}🟢extract_rendered(url, format, maxChars, section)
Same output as /extract, but the page is first rendered in a real browser, so single-page apps and pages that build their content with JavaScript come back with their text instead of an empty shell. Waits for the network to settle (up to 15 seconds). Public pages only; no login. Use when /extract returns EXTRACTION_EMPTY or too little text for a page you can read in a browser. Example: url=https://example.com/. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute public http(s) URL of the page"
},
"format": {
"type": "string",
"enum": [
"text",
"markdown",
"both"
],
"description": "text (default), markdown or both"
},
"maxChars": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "Output limit, 500-100000 characters (default 20000)"
},
"section": {
"type": "string",
"description": "Optional exact HTML id to read only that element"
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢pdf_text(url, firstPage, pages, maxChars)
Extract the text of a public PDF (up to 10 MB) from its URL, page by page, with title, author and page count. Choose the first page, how many pages (up to 200) and maxChars. arXiv abstract links work. If a site blocks our fetch, the Internet Archive's dated copy is read and the answer says so. Scanned, encrypted and non-PDF files fail uncharged. Use to read papers, invoices, reports and manuals into an agent. Example: url=https://bitcoin.org/bitcoin.pdf. Price $0.005/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute public http(s) URL of the PDF"
},
"firstPage": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "First page to read (default 1)"
},
"pages": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many pages to read (1-200, default 20)"
},
"maxChars": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "Maximum characters of text returned across all pages (1000-200000, default 50000)"
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢document_text(url, format, maxChars)
Convert a document to text or Markdown: Word (.docx) with headings, lists and tables, Excel (.xlsx) sheet by sheet, PowerPoint (.pptx) slide by slide, a PDF's text, and scanned PDFs or images (PNG, JPEG, WebP) by OCR. Give a public file's URL, or send the file in a POST body (10 MB; images 3 MB). Old .doc/.xls/.ppt and password-protected files fail uncharged. Use to read attachments, scans and spreadsheets into an agent, RAG or a workflow. Example: url=https://calibre-ebook.com/downloads/demos/demo.docx. Price $0.005/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute public http(s) URL of the file (or send the file in a POST body instead)"
},
"format": {
"type": "string",
"enum": [
"markdown",
"text"
],
"description": "markdown (default: headings, lists and tables kept) or text"
},
"maxChars": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "Maximum characters of text returned (1000-200000, default 50000)"
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢document_extract(url, fields)
Extract named fields from a document as JSON: give a PDF, Word, Excel or PowerPoint file, a scan or a photo (PNG, JPEG, WebP) by URL or in a POST body (up to 10 MB; images 3 MB) and the field names you want, such as invoice_number, total, due_date. An AI model reads the file, scans by OCR, and returns one JSON object, with null where a value is not stated. Use to turn invoices, receipts, orders and contracts into rows. Price $0.03/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute public http(s) URL of the file (or send the file in a POST body instead)"
},
"fields": {
"type": "string",
"description": "Comma-separated field names to extract (1-30). For rows, give the row keys in brackets: line_items[description,quantity,amount]. Or one word, invoice or receipt, for the usual fields of that document with its line items"
}
},
"required": [
"url",
"fields"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence