Skip to content
MCP server

Image OCR Text Extractor: extract text from images

Extract text, Markdown and word boxes from images with offline Tesseract OCR

Install
Pricing
Freemium
Platforms
Web, API
Runs
Remotely
Access
Needs an account or API key
Version
1.0.0
Listing updated
2 days ago

About Image OCR Text Extractor: extract text from images

Image OCR Text Extractor: extract text from images is a freemium MCP server for files and documents. It runs as a hosted remote server, so there is nothing to install locally.

Images go in as links or uploaded files and come out as one row each, holding plain text, Markdown, line and word counts, mean confidence and optionally every word's pixel box. The Markdown step turns large short lines into headings, joins hyphenated breaks and keeps lists and table rows. OCR runs inside the Actor with the open-source Tesseract library, so nothing is sent to an outside OCR service or AI model.

It reads 29 languages, several at once for mixed documents, and minConfidence drops uncertain words; the page suggests 50 to 60 for phone photos. Limits: 500 images per run, 20 MB per file by default, and skipped files above 100 million pixels. Handwriting is not a stated strength.

It is an Apify Actor priced at $2 per 1,000 processed images; failed images are free.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

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

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

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

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

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

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

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

What it does

Offline OCR
Tesseract runs in the Actor; no external service.
Markdown output
Headings, lists and table rows preserved.
Word boxes
Pixel position and confidence per word.
29 languages
Several per image.
Confidence filter
minConfidence removes uncertain words.

Good for

  • Digitise scanned letters and forms
  • Read receipts before parsing amounts
  • Feed screenshots into a knowledge base
  • Locate words to highlight or redact

Pricing

Freemium

$2 per 1,000 images; Apify free plan includes $5 monthly credit

Prices change. Check apify.com before you buy.

Image OCR Text Extractor: extract text from images FAQ

Is image data sent elsewhere?

No, OCR runs inside the run.

What formats work?

PNG, JPEG, WebP, BMP and PBM/PGM/PPM.

What does it cost?

$2 per 1,000 processed images.

How many images per run?

Up to 500.

Is Image OCR Text Extractor: extract text from images free?

Image OCR Text Extractor: extract text from images has a free plan, with paid plans for more usage or features.

How do I add Image OCR Text Extractor: extract text from images to Claude Code?

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

What are the best alternatives to Image OCR Text Extractor: extract text from images?

The closest alternatives to Image OCR Text Extractor: extract text from images are REA, HyperFrames by HeyGen, Codebase Memory, GitHub and Serena MCP: the IDE for your agent.

Alternatives to Image OCR Text Extractor: extract text from images

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Hosted MCP connector for creating and rendering videos from HTML through AI chat

    • Remote
    • Freemium
    • 85.3K GitHub stars
    • Design and media
  3. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  4. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  5. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  6. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory