Skip to content
MCP server

Bulk OCR: Images & Scanned PDFs to Text (Tesseract)

Bulk OCR of scanned PDFs and images to text, one row per page, via Apify

Responds, sign-in requiredStatus and history

The server answered 3 hours ago but needs an account or API key, so we could not list its tools.

Pricing
Paid
Platforms
API, Web
Runs
Remotely
Access
Needs an account or API key
Version
0.1.0
Listing updated
2 days ago

About Bulk OCR: Images & Scanned PDFs to Text (Tesseract)

Bulk OCR: Images & Scanned PDFs to Text (Tesseract) is a paid MCP server for files and documents. It runs as a hosted remote server, so there is nothing to install locally.

Files go in as direct links or from a key-value store you filled in Apify Console, and text comes out one row per page with word count, an OCR confidence from 0 to 100 and whether the text came from OCR or the PDF's own text layer. It runs the open-source Tesseract engine with Poppler for PDFs, with no third-party API or key; files are downloaded into the run's container and deleted when it ends.

Supported inputs are PNG, JPEG, multi-page TIFF, GIF, BMP and WebP, and PDFs rendered at 300 DPI by default. Nine languages are available: English, German, French, Spanish, Italian, Portuguese, Dutch, Polish and Turkish, and mixed-language documents work by selecting several.

Limits are stated: 50 MB per file, 1,000 files per run, 2,000 pages per file, no handwriting and no password-protected PDFs. Tables come out as text lines rather than cells. Billing is per page that yields text; blank and failed pages are free.

Install

Run in a terminal

claude mcp add --transport http bulk-ocr 'https://mcp.apify.com/?tools=stellalytics/bulk-ocr'

Add to Settings → Connectors → Add custom connector

https://mcp.apify.com/?tools=stellalytics/bulk-ocr
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "bulk-ocr": {
      "url": "https://mcp.apify.com/?tools=stellalytics/bulk-ocr"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "bulk-ocr": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=stellalytics/bulk-ocr"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "bulk-ocr": {
      "serverUrl": "https://mcp.apify.com/?tools=stellalytics/bulk-ocr"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "bulk-ocr": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=stellalytics/bulk-ocr"
    }
  }
}

What it does

Per-page rows
Each page returns text, words, confidence and method.
Nine languages
English, German, French, Spanish, Italian, Portuguese, Dutch, Polish and Turkish.
PDF text layer reuse
Pages that already contain text are read directly unless you turn it off.
Error rows per file
A bad link or damaged PDF gives one error row while others continue.
Cost caps
Set maximum pages or a maximum cost per run.
Run summary
A SUMMARY record counts files, pages, charged, blank and failed.

Good for

  • Turn scanned contracts and invoices into searchable text
  • Feed scanned PDFs to an LLM or RAG index page by page
  • Digitise archives at a fixed price per page
  • Chain OCR after another Actor that saves files
  • Send results to Sheets, Slack or n8n

Pricing

Paid

From $3.00 per 1,000 page reads plus Apify's start fee

Prices change. Check apify.com before you buy.

Bulk OCR: Images & Scanned PDFs to Text (Tesseract) FAQ

What does it cost?

From $3.00 per 1,000 page reads plus Apify's start fee; blank and failed pages are not charged.

Can it read handwriting?

No. Handwriting is not supported.

Where do my files go?

They are read inside the run and deleted when it ends; nothing is sent to a third-party service.

How accurate is it?

Clean 300 DPI scans usually read with confidence above 90; low-resolution photos and complex tables read worse.

Is Bulk OCR: Images & Scanned PDFs to Text (Tesseract) free?

No. Bulk OCR: Images & Scanned PDFs to Text (Tesseract) is a paid product.

How do I add Bulk OCR: Images & Scanned PDFs to Text (Tesseract) to Claude Code?

Run this command in your terminal: claude mcp add --transport http bulk-ocr 'https://mcp.apify.com/?tools=stellalytics/bulk-ocr'

What are the best alternatives to Bulk OCR: Images & Scanned PDFs to Text (Tesseract)?

The closest alternatives to Bulk OCR: Images & Scanned PDFs to Text (Tesseract) are HyperFrames by HeyGen, ffmpeg-skill, ASTra, AvatarSay — Fictional Character & Talking Video MCP and ChartAnt.

Alternatives to Bulk OCR: Images & Scanned PDFs to Text (Tesseract)

  1. Hosted MCP connector for creating and rendering videos from HTML through AI chat

    • Remote
    • Freemium
    • 85.3K GitHub stars
    • Design and media
  2. ffmpeg-skill

    MCP server

    Local FFmpeg video and audio editing tools for coding agents over MCP

    Runs locally
    • Open source
    • 6.9K GitHub stars
    • Design and media
  3. ASTra

    MCP server

    Let agents read, edit, validate and undo Word .docx files with exact operations

    Runs locally
    • 5 tools
    • Freemium
    • Files and documents
  4. ChartAnt

    MCP server

    Remote MCP server returning charts, maps and dashboards as hosted PNG links

    • 51 tools
    • Remote
    • Freemium
    • Design and media
  5. VfxSmith

    MCP server

    Search, generate, refine and export pixel art game effects from Claude Code or Codex

    Not checked yet
    • Remote
    • Freemium
    • Design and media