What it does
The server exposes one tool, media_extract_text_from_image, which accepts an image URL or base64-encoded image data. It returns the extracted text, word count, confidence score and detected language. An optional language hint, such as eng, fra or deu, guides recognition, and the default is eng.
Use it when text needs to be pulled out of an image. The publisher directs web page text, PDF text and screenshots to other tools.
To run it, add the server to an MCP client configuration such as Claude Desktop, Cursor or ElizaOS. Each call costs $0.012, paid over HTTP using the x402 protocol in USDC on Base L2. No API key or signup is needed, but an x402-aware client, such as @x402/fetch, must handle the payment step. The project is released under the MIT license.
Limitations and requirements
Each call is charged $0.012 in USDC on Base L2, so a wallet and an x402-aware client are required. The publisher states the tool is not meant for web page text, PDF text or screenshots.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
OCR Text Extraction API
Extract text from images using OCR. Tesseract-powered. x402 micropayment.
v1.1.0As shown on registry.modelcontextprotocol.io when we last read it