# OCR Text Extraction — Image to Text, Multi-Language

OCR Text Extraction — Image to Text, Multi-Language is a Claude Code MCP server that reads text from images supplied by URL or base64. Use it to process documents, receipts, and screenshots.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 3557 installs
- Author: axel-belfort
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/axel-belfort/ocr-extract
- Updated: 2026-04-12
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/ocr-text-extraction-image-to-text-multi-language

## What it does

The server extracts image text and reports a confidence score and the language it detects. Its `media_extract_text_from_image` tool accepts either an image URL or base64-encoded data, with support for multiple languages.

No API key is needed. Each call costs $0.005 and uses an x402 micropayment on Base L2. Claude Code setup offers two commands: one registers the server as `ocr-extract`, and the other uses its full name.

## Requirements
- Remote server: `https://ocr-extract--axel-belfort.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http ocr-extract https://ocr-extract--axel-belfort.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add ocr-text-extraction-image-to-text-multi-language --url https://ocr-extract--axel-belfort.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "ocr-text-extraction-image-to-text-multi-language": {
            "url": "https://ocr-extract--axel-belfort.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "ocr-text-extraction-image-to-text-multi-language": {
            "type": "http",
            "url": "https://ocr-extract--axel-belfort.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http ocr-text-extraction-image-to-text-multi-language https://ocr-extract--axel-belfort.run.tools
```

## When to use it
- extract text from an image URL
- read text from a screenshot encoded in base64
- retrieve document text with its detected language and confidence score

## Example prompts
- Extract the text from this image URL.
- Read the text in this base64 screenshot.
- Get the text from this receipt.

## Similar
- [paddleocr-text-recognition](https://affpapa.org/en/nevibecode/skills/paddleocr-text-recognition.md) — skill · 4000 installs
- [PDF OCR Extraction](https://affpapa.org/en/nevibecode/skills/pdf-ocr-extraction.md) — skill · 6000 installs
- [image-ocr](https://affpapa.org/en/nevibecode/skills/image-ocr.md) — skill · 1 install
- [ocr-super-surya](https://affpapa.org/en/nevibecode/skills/ocr-super-surya.md) — skill · 561 installs
- [ocr](https://affpapa.org/en/nevibecode/skills/ocr.md) — skill · 509 installs
- [image-to-text](https://affpapa.org/en/nevibecode/skills/image-to-text.md) — skill · 725 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
