Extract readable text from images, screenshots, photos, and scanned PDFs via OCR. Returns reading-order text with confidence and optional bounding boxes for receipts, invoices, and forms.
MIT
649,985 tools. Updated 2026-10-08 22:49
"Tools for Reading Text from PDFs and Images" matching MCP tools:
- Read non-markdown vault files like images, canvases, PDFs, and text as agent-readable content, with line paging for large files.MIT
- Lists non-markdown files in an Obsidian vault or folder—images, PDFs, canvases, data—with byte sizes and extension counts for discovery before reading.MIT
- Retrieve the original documents a crawl captured—PDFs, office files, images, CSVs—with download URLs for when you need the actual files, not just extracted text.MIT
- Generate images from text prompts, optionally with reference images for editing. Returns finished image URLs and previews.MIT
- Add text annotations, images, and fill form fields in PDF files. Modify scanned PDFs with links, shapes, and external content.MIT
Matching MCP Servers
- FlicenseAqualityDmaintenanceEnables document conversion between PDF, DOCX, and Markdown formats to facilitate reading and editing complex files in AI tools like Claude Desktop or Cursor. It utilizes marker-pdf and pandoc to provide structured text versions of documents, helping to manage context and support unsupported file types.11-
- AlicenseAqualityCmaintenanceEnables generating images through SmartAPI's image generation endpoint directly from Codex, saving files locally.1MIT
Matching MCP Connectors
Exact character/word counting, reversal, palindrome checks, indexing, sorting; Unicode-safe.
Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.
- View attachments from Todoist comments by providing the fileUrl from the comment's fileAttachment field. Renders images inline, returns text as text, and embeds binary files like PDFs.MIT
- Retrieve your past render results including images, PDFs, and screenshots. Filter by template or batch, and paginate to navigate through results.Apache 2.0
- Create images from text descriptions. Choose size, style, model, and number of images to generate.MIT
- Retrieve a curated list of featured AI workflows for generating images, text, and other content.MIT
- Extract text and embedded images from a PDF, saving them as separate text and image files for reuse.MIT
- Extract clean text and table markdown from images using AI vision. Simplifies OCR for web scraping and data processing.MIT
- Convert PDFs and scanned images into JSON representation, preserving text, fonts, images, vectors, and formatting.MIT
- Extract structured content and layout from PDFs, images, and Office files. Supports output formats like HTML, text, and markdown.MIT
- Extract structured content from PDFs, images, and Office files while preserving original formatting and layout using Upstage AI's document digitization API.MIT
- Extract text from PDFs with Y-coordinate reading order. Handle multi-column layouts and compact whitespace for Japanese forms to reduce token consumption.MIT
- Read any file from an Obsidian vault, including PDFs, images, and data files, with auto text, inline image, or base64 encoding.MIT
- Extract text from USPTO petition documents using hybrid extraction: free PyPDF2 for text-based PDFs, Mistral OCR for scanned documents. Analyze legal arguments, issues, and patterns in petition decisions.MIT
- Extract text from local images and PDFs with Apple Vision OCR, returning plain text or structured blocks with bounding boxes. Works offline on macOS.MIT
- Extract text, faces, barcodes, and rectangles from images and PDFs in reading order for document reconstruction. Works fully offline with no API keys.MIT
- Fetch a single email attachment by ID, extract text from PDFs, Office docs, and images via OCR, and save it to Downloads.MIT