Skip to content
MCP server

Image to Text OCR

Tesseract-based OCR for images and screenshots in 27 languages, billed per image with text

Install
Pricing
Freemium
Platforms
API, Web
Runs
Remotely
Version
1.0.0
Listing updated
2 days ago

About Image to Text OCR

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

The server runs the open-source Tesseract 5 engine inside an Apify Actor, so it does not depend on scraping Google Lens and avoids that route's captchas and rate limits. Give it image URLs, including Google Drive and Dropbox share links, and each one returns text, Markdown, a 0 to 100 confidence score and a word count.

Billing is unusual: you pay only for images where text is found, while blank images, broken links and unsupported files cost nothing. The confidence score lets you send weak scans to a human. The page advises picking only the languages present in the image, since one to three languages run faster and more accurately, and notes that handwriting is poorly supported.

It does not return form or table structure the way Textract does. For scanned PDFs the author points to a separate PDF OCR Actor.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

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

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

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

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

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

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

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

What it does

27 OCR languages
Reads Latin, Cyrillic, Arabic, Hebrew, Hindi, Thai, Chinese, Japanese, Korean and more, mixed in one run.
Confidence score
Each image gets a 0 to 100 score for routing poor scans to review.
Many formats
Handles PNG, JPEG, multi-page TIFF, WebP, BMP and GIF.
Free when blank
Blank images, broken links and unsupported files are not charged.
Text and Markdown output
Returns plain text, Markdown or both per image.
Spend cap
A maximum cost per run stops the Actor cleanly.

Good for

  • Digitise receipts, invoices and labels
  • Pull text from screenshots and slides for search or moderation
  • Feed text from images into an AI agent or RAG pipeline
  • Bulk-index scanned archives in TIFF

Pricing

Freemium

$1.50 per 1,000 images with text; Apify's free plan includes $5 of usage every month.

Prices change. Check apify.com before you buy.

Image to Text OCR FAQ

How much does it cost?

$0.0015 per image with text ($1.50 per 1,000), with no start fee and no charge for blank images.

Does it read handwriting?

Only neat, print-like handwriting, because Tesseract is built for printed text.

What is the file size limit?

50 MB per image by default, adjustable up to 500 MB.

Does it handle PDFs?

No, the page points to the author's PDF to Text and Markdown Actor for that.

How do I connect it to Claude?

Add https://mcp.apify.com?tools=poised_beardlichen/image-to-text-ocr as a custom connector and sign in to Apify.

Is Image to Text OCR free?

Image to Text OCR has a free plan, with paid plans for more usage or features.

How do I add Image to Text OCR to Claude Code?

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

What are the best alternatives to Image to Text OCR?

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

Alternatives to Image to Text OCR

  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