A flexible OCR server using EasyOCR wrapped in a Model Context Protocol (MCP) interface. Supports base64, file, or URL inputs, multi-language configurations, and returns both text-only and detailed OCR results. Easy to integrate into MCP-driven AI workflows—just set your `EASYOCR_LANGUAGES`, run the server, and call `ocr_image_*` tools.
1 file for Codex and OpenCode: easyocr-mcp AGENTS.md — 371 tokens loaded in every session.
AGENTS.md A 371 tok These files are WindoC/easyocr-mcp's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.