Free during launch: every app and tool is unlimited — no account, no card. Purchases open soon (then $9 once). Download · Free browser tools
GUI Hub
For Claude, Cursor, VS Code & other MCP clients

Can Claude read and search my scanned PDFs?

Not on its own. Claude can read a short scan you attach to a chat, but it can’t open the scanned PDFs on your disk, and a folder of hundreds of private pages (contracts, tax papers, medical letters) is not something to upload page by page. This runs OCR locally and leaves a searchable PDF you keep, plus a text file the AI can read and search. With the GUI Hub Essentials MCP server installed, Claude (Desktop or Code), Cursor, VS Code and other MCP clients can make scanned PDFs searchable and read what they say (OCR, offline) locally: the assistant calls the ocr_pdf tool, which runs Rescribe on your machine. Files are not uploaded.

Set it up (2 minutes)

  1. Claude Code / Cursor / VS Code / Windsurf: add the MCP server
    npx -y https://guihub.cc/mcp.tgz --product=essentials
    Claude Code: claude mcp add gui-hub-essentials -- npx -y https://guihub.cc/mcp.tgz --product=essentials
  2. Claude Desktop: download the one-file extension and double-click it.
  3. No AI? GUI Hub Essentials is also a point-and-click desktop app.

Agent with its own computer?

Grok Bot, ChatGPT dots, Claude Duet, OpenClaw, Manus or Codex can run it directly — no MCP needed:

npx -y https://guihub.cc/cli.tgz run ocr_pdf --input /path/to/input.pdf --outDir /path/to/folder

Options: npx -y https://guihub.cc/cli.tgz info ocr_pdf · skill file: SKILL.md · more for agents

Then ask

“Make every scanned PDF in my Documents/Scans folder searchable, then find the lease that mentions the parking space.”

What the AI gets

ocr_pdf — Make a scanned (image-only) PDF searchable on the user's computer, offline: OCR every page (Tesseract via Rescribe) and save `<name> searchable.pdf` (same look, selectable/searchable text layer) plus `<name>.txt` (all the text) into `outDir`. Use for 'make this scan searchable', 'what does this scanned contract/invoice/letter say', 'extract text from my scanned PDFs', especially for long or private documents that should not be uploaded. Set `lang` to the document's language. Then read the .txt to answer questions about the document. Works with PDFs whose pages are JPEG/PNG/TIFF images (scanners, phone scan apps); if it reports an unsupported image type, export the pages as images and use ocr_folder.

InputType
input*string
langstring (eng, deu, fra, spa, ita, por)
outDir*string

Cost

Free to install; each tool has 3 free uses. Then $9 once for all of GUI Hub Essentials (no subscription). The tool tells the assistant when free uses run out and how to unlock.

Powered by Rescribe (GPL-3.0 (Rescribe, with embedded Tesseract: Apache-2.0); Apache-2.0 (tessdata_fast language models)), the official release, verified by SHA-256. GUI Hub is independent and not affiliated with Rescribe, Anthropic, Cursor or Microsoft.

Other things your AI can do with GUI Hub