# Agent Data Tools: Documents to text

> Agent Data Tools: Documents to text is a freemium MCP server for files and documents. Convert PDF, Word, Excel, PowerPoint and web pages to Markdown, and pull invoice fields. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://agent-data-tools.revmesh2074.workers.dev
- **Repository:** https://github.com/nutshell2000/agent-data-tools
- **MCP Registry name:** io.github.Nutshell2000/agent-data-tools-documents
- **Categories:** files and documents
- **Listing updated:** 2026-11-14

## About

A document-reading slice of the Agent Data Tools catalogue with five tools. They turn PDF, Word, Excel, PowerPoint and web pages into Markdown for a model to read, and extract invoice fields as JSON. A separate PDF to text API returns text page by page as JSON from a URL, and a web page to Markdown API offers a rendered reader for JavaScript pages.

The catalogue's static reader handles public HTML, Markdown and plain text only, with no JavaScript rendering, authenticated pages or paywall access, and a public documentation page costs $0.002 USDC per successful call. Preserved code blocks and tables are shown in the site's demonstration. Over HTTP PDF reading is not part of the free trial.

The first 25 successful calls over MCP are free and failed calls are not charged. After that, pay per call with USDC through x402 or buy prepaid card credits from $1. Developer API plans start at $9 a month.

## Features

- **Office to Markdown:** Converts Word, Excel and PowerPoint files to Markdown.
- **PDF reading:** Extracts PDF text for models, page by page through the API.
- **Web page to Markdown:** Reads public pages as clean text with code and tables preserved.
- **Invoice fields:** Returns invoice data as JSON.
- **Public pages only:** Static pages without logins, paywalls or JavaScript rendering on the basic reader.
- **Pay per call:** Free starter calls, then USDC or prepaid card credits.

## Good for

- Feed a PDF contract into an assistant as text
- Turn a spreadsheet into Markdown for analysis
- Extract amounts and dates from invoices
- Read a documentation page with its code samples

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http agent-data-tools-documents https://agent-data-tools.revmesh2074.workers.dev/mcp/documents
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://agent-data-tools.revmesh2074.workers.dev/mcp/documents
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agent-data-tools-documents": {
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/documents"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "agent-data-tools-documents": {
      "type": "http",
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/documents"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agent-data-tools-documents": {
      "serverUrl": "https://agent-data-tools.revmesh2074.workers.dev/mcp/documents"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "agent-data-tools-documents": {
      "type": "http",
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/documents"
    }
  }
}
```

## Tools

- `extract`: 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
- `extract_rendered`: 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:/
- `pdf_text`: 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 in
- `document_text`: 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 spr
- `document_extract`: 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 an

## FAQ

### Which formats are supported?

PDF, Word, Excel, PowerPoint and web pages, with invoice fields returned as JSON.

### Can it read pages behind a login?

The static reader does not handle authenticated or paywalled pages.

### What does a page read cost?

The site lists a public documentation page at $0.002 USDC per successful call.

### Is PDF reading free over HTTP?

No. PDF reading is not part of the free HTTP trial, though the first 25 MCP calls are free.

### Is Agent Data Tools: Documents to text free?

Agent Data Tools: Documents to text has a free plan, with paid plans for more usage or features.

### How do I add Agent Data Tools: Documents to text to Claude Code?

Run this command in your terminal: claude mcp add --transport http agent-data-tools-documents https://agent-data-tools.revmesh2074.workers.dev/mcp/documents

### What are the best alternatives to Agent Data Tools: Documents to text?

The closest alternatives to Agent Data Tools: Documents to text are ASTra, CARTESIAN ECU, Invoices, SigPen and ConvertAudioToText.

## Alternatives

- [ASTra](https://ai-powered.com/mcp/astra): ASTra is a freemium MCP server for files and documents.
- [CARTESIAN ECU](https://ai-powered.com/mcp/cartesian-ecu): CARTESIAN ECU is a paid MCP server for files and documents.
- [Invoices](https://ai-powered.com/mcp/invoices): Invoices is a paid MCP server for files and documents.
- [SigPen](https://ai-powered.com/mcp/sigpen): SigPen is a freemium MCP server for files and documents.
- [ConvertAudioToText](https://ai-powered.com/mcp/convertaudiototext): ConvertAudioToText is a freemium MCP server for design and media.
- [WhoScribe](https://ai-powered.com/mcp/whoscribe): WhoScribe is a freemium MCP server for design and media.
- [filex](https://ai-powered.com/mcp/filex): filex is an open-source MCP server for files and documents.
- [DocJacket](https://ai-powered.com/mcp/docjacket): DocJacket is a freemium MCP server for productivity.

---
Source: https://ai-powered.com/mcp/agent-data-tools-documents-to-text
