Convert PDF, Office documents, images, and web pages to Markdown with OCR support and page range extraction.
Apache 2.0
206,568 tools. Last updated 2026-06-17 14:27
"High-Quality PDF Extraction to Text with Tokenization and Accurate Processing of Complex Layouts" matching MCP tools:
- Submit a receipt image or PDF for asynchronous AI extraction of receipt data. Receive a job ID to poll for status, with optional webhook notification. Returns extracted data for further processing.MIT
- Check the status of an asynchronous receipt extraction job. Provide the job ID to get the current status: pending, processing, completed, or failed.MIT
- Add documents to a collection by providing a URL for download, processing them for text extraction, and indexing them for semantic search.MIT
- Retrieve Echo3s technical specifications—supported formats, AI processing details, output quality, credit system, and platform info.MIT
- Save a full-quality PNG screenshot to disk for high-resolution reporting, debugging, or sharing.Apache 2.0
Matching MCP Servers
- -license-quality-maintenanceConverts PDF files to text for use with MCP-compatible applications like Cursor IDE.Last updated
- FlicenseCqualityDmaintenanceAn MCP server that provides a tool to extract text content from local PDF files, supporting both standard PDF reading and OCR capabilities with optional page selection.Last updated130
Matching MCP Connectors
EBI Complex Portal MCP.
Create and manage trackable QR codes with scan tracking, analytics, and dynamic URL updates.
- Extract data from receipt images and generate expense reports as PDF, DOCX, or ODT in one step, using AI extraction and customizable templates.MIT
- Securely replaces sensitive plaintext values with vault tokens, enabling reversible detokenization while preserving data utility. Supports deterministic tokenization for consistent token mapping.GPL 3.0
- Extract all text content from a PDF. Input the PDF as a base64-encoded string and receive the extracted text.MIT
- Convert PDF and scanned documents to CSV files, preserving layout and table structure for data extraction.MIT
- Convert PDF and scanned images to text while preserving layout. Supports URL input, optional page ranges, and OCR language selection.MIT
- Convert PDF files and scanned images to XML format for data extraction and further processing.MIT
- Remove the text layer from a PDF to make it non-searchable, preventing text extraction and search functionality.MIT
- Convert PDFs and scanned images to JSON while preserving text, fonts, images, vectors, and formatting using the /pdf/convert/to/json2 endpoint.MIT
- Parse any PDF to extract text and tables, returning structured JSON for flexible data processing.MIT
- Extract the table of contents from a PDF attachment as a hierarchical markdown list with page numbers, helping you quickly orient in a paper before fetching full text.MIT
- Extract PDF page layout including text, coordinates, fonts, and colors to understand document structure before making edits.MIT
- Converts PDF to reading-order Markdown for LLM consumption. Reconstructs up to 2 content columns, infers headings from font size, detects lists; tables rendered as plain text.MIT
- Convert Markdown to PDF with support for headings, lists, tables, code blocks, and more. Returns a base64-encoded PDF file.MIT
- Extract structured data from documents using custom field definitions, combining information from multiple files into a single record with enhanced AI accuracy for complex layouts and low-quality scans.MIT