"How to scrape data from websites into JSON" matching MCP connectors:

Generate PDF/DOCX/XLSX/PPTX from templates+JSON. Convert Office/HTML/MD to PDF. Universal templating

Fill any PDF form from your AI agent — in a single tool call.

Compress PDFs to exact target sizes (82-93% smaller). Tools: compress_pdf, optimize_pdf, inspect_pdf

Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.

Compiles source-agent outputs into validated, receiver-ready handoff packages.

Generate professional receipt PDFs and structured receipt data with AI-ready MCP tools.

Generate PDF, Word (.docx) and PowerPoint (.pptx) documents from Markdown over MCP.

Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.

Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.

Deploy files, sites, and Dockerfile apps to live URLs + private drives for agent memory.

DocWand signs and fills PDFs without uploading them anywhere. Attach a PDF to the chat and say what you need — "fill out this form and sign it with my name" — and DocWand opens an interactive widget: form fields pre-filled from your message, a handwritten-style signature ready to place, checkboxes you tick with one click, and click-to-type on flat documents. The whole PDF engine runs inside the wi

Sandbox workspace tools: search, file read, DB queries, integrations. Returns synthetic data.

This is a Unified MCP Server for full document control: PDF manipulation (merge, split, rotate, insert, delete), OCR/data extraction from PDFs/images, PDFs/images conversion, compression, encryption, and watermark management—all without juggling multiple tools.

20 free dev tools: JSON/YAML, XML/SQL, Cron, SEO, QR code, URL shortener, cron tasks, files

Real .docx and .xlsx files from structured data, with automatic Hebrew/Arabic RTL.

Tigris MCP Server seamlessly connects AI agents to Tigris bucket and object management.

MCP server for Api2Pdf — generate PDFs & images from HTML, URLs or office files; merge, barcodes.

Document generation MCP server. Turn BulkRender templates into DOCX and PDF files directly from Claude, Cursor, Windsurf, and any MCP compatible assistant. Supports agent walk in.

Hosts AI-generated web content (HTML, images, SVG, JSON) at a public URL, with custom domains.

Browse and manage files in your Moxt AI workspace from any MCP client.