Odel
OCR Text Extraction API

OCR Text Extraction API

@br0ski777TypeScriptMITUpdated 4 days ago

Extract text from images using OCR. Tesseract-powered. x402 micropayment.

View on GitHubSign in to connect
Server endpointStreamable HTTPNo authProbed

Registry lists this as SSE; the live endpoint answered over Streamable HTTP.

https://ocr-extract.api.klymax402.com/mcp

This is the third-party server itself — Odel doesn't run it. Hitting this URL directly talks straight to the upstream server with no auth or proxying. Connect through Odel to front it with managed auth.

OCR Text Extraction API

MCP Server x402 License: MIT

Extract text from images using OCR. Supports URLs and base64 images. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.

Part of the klymax402 marketplace -- 100 x402 micropayment APIs for AI agents, one wallet, USDC on Base.

Quickstart -- MCP

Add to your MCP client config (Claude Desktop, Cursor, ElizaOS, etc.):

{
  "mcpServers": {
    "ocr-extract": {
      "url": "https://ocr-extract.api.klymax402.com/mcp"
    }
  }
}

Quickstart -- HTTP (x402)

curl -X POST "https://ocr-extract.api.klymax402.com/api/ocr" \
  -H "Content-Type: application/json" \
  -d '{}'
# -> 402 Payment Required, with an x402 payment challenge in the response body

Any x402-aware client (@x402/fetch, x402-agent-tools, ATXP) handles the 402 -> sign -> retry cycle automatically.

Tools

ToolMethodPathPriceDescription
media_extract_text_from_imagePOST/api/ocr$0.012Extract text from an image via OCR

media_extract_text_from_image

Use this when you need to extract text from an image. Accepts an image URL or base64-encoded image data. Returns the extracted text, word count, confidence score, and detected language. Do NOT use for web page text extraction — use web_scrape_to_markdown instead. Do NOT use for PDF text extraction — use document_generate_pdf instead. Do NOT use for taking screenshots — use capture_screenshot instead.

Parameters

NameTypeRequiredDescription
image_urlstringnoURL of the image to extract text from
image_base64stringnoBase64-encoded image data (alternative to image_url)
languagestringnoLanguage hint for OCR: eng, fra, deu, spa, etc. (default: eng)

Example agent prompts

  • "Extract text from an image"

Payment

  • Protocol: x402 -- HTTP-native pay-per-call, no signup, no API key
  • Network: Base L2 (eip155:8453)
  • Asset: USDC
  • Facilitator: Coinbase CDP (primary), PayAI (fallback)

Part of klymax402

100 x402 micropayment APIs for AI agents -- one wallet, USDC on Base, zero signup.

License

MIT