Every FABX tool, inside your AI.
Ask Claude or ChatGPT to "compress this photo to 20 KB" or "merge these three PDFs and Bates-number them" — and FABX does it. One connector, all the tools, no tab-switching.
How it works
3 stepsPaste one URL
In Claude → Settings → Connectors (or ChatGPT → Apps), add mcp.fabxlabs.com. One approval, done.
Say it in plain words
"Shrink this to under 100 KB", "split this PDF into 5 MB parts", "make a UPI QR for ₹500". Your AI picks the right FABX tool.
File comes back
Processed and returned in the chat. Files are processed in memory and deleted immediately — nothing is stored.
Tools the connector exposes
one connector · 19 toolscompress_image_to_20kbReduce a JPG or PNG to an exact size in KB for exam forms and government portalsresize_imageResize a photo to exact pixel dimensions or centimetres with presets for SSC, IBPS, UPSC, passport and PANpassport_photoTurn any photo into a passport size photo (3.5 × 4.5 cm or 2 × 2 inch) with the right pixel size and KB limit for online applicationssignature_resizeResize a scanned signature to 10–20 KB and the exact pixel size asked by SSC, IBPS, SBI, RRB and UPSC formsconvert_imageConvert images between PNG, JPG and WebP in your browserjpg_to_pdfConvert JPG, PNG or WebP images into a single PDF, A4 or original size, with marginscompress_pdf_to_100kbReduce a scanned PDF to an exact size in KB for government portals, GST, income tax and exam uploadspdf_to_jpgConvert PDF pages to JPG or PNG images at the resolution you choosemerge_pdfCombine several PDFs into one in the order you choosesplit_pdfSplit a PDF by page ranges, every N pages, one file per page or by maximum file sizesplit_pdf_by_sizeSplit a large PDF into parts under a size limit (for example 5 MB for GST or 10 MB for email), keeping pages in orderorganize_pdfDrag PDF pages to reorder, rotate or delete them with thumbnails, and mix pages from several filesextract_pdf_pagesPull selected pages out of a PDF into a new file, in any orderrotate_pdfRotate every page or specific pages of a PDF by 90, 180 or 270 degrees and savepage_numbersStamp page numbers ("Page 1 of 20", "1", "- 1 -") on a PDF at any position and font size, across one or many filesbates_numberingStamp Bates numbers (EXH-000123) with prefix, start number, zero padding and suffix, running continuously across a bundle of PDFsinspect_pdfSee page count, page sizes in mm, author, creator, dates and whether a PDF is encryptedqr_code_generatorMake a QR code for a link, UPI payment, WhatsApp chat, Wi-Fi or textword_counterCount words, characters (with and without spaces), sentences and paragraphs, with reading time and frequent words
Why one connector, not many
You add it once. Your AI sees every tool by name and chooses the right one for the job — image, PDF or QR. Same privacy rule as the website: no accounts on your files, no storage, no training on your data.
- 1
- connector to add
- 19
- tools inside it
- 0
- files stored
- ₹0
- free tier
Questions
What is an MCP connector?
Model Context Protocol is the open standard AI assistants use to call outside tools. Claude, ChatGPT, Cursor and many agents support it. A connector is just a URL you add once; after that the assistant can use the tools it provides.
Is it free?
There will be a free tier for personal use and paid keys for higher volume and teams. Pricing is announced at launch; waitlist members get early access.
Are my files uploaded?
Unlike the website tools, the connector processes files on our servers so your AI can hand them over. Files are held in memory only for the seconds needed and are never stored or used for training. If you need zero-upload processing, use the browser tools.
Can I use it in my own app or script?
Yes — the same endpoint works as a plain HTTP API with an API key. Documentation ships with the launch.