ddddocr

ddddocr rust 版本，ocr_api_server rust 版本，二进制版本，验证码识别，不依赖 opencv 库，跨平台运行，AI MCP 支持，a simple OCR API server, very easy to deploy。

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio 86maid-ddddocr docker run -i 86maid/ddddocr \
  --env PORT="API listening port (default 8080)" \
  --env LOG_LEVEL="info|debug|warn|error (default: info)"

How to use

ddddocr provides a ready-to-run OCR API server implemented in Rust. It bundles an OCR engine that can classify single-line text, detect text regions, and perform slider-like matching functionality through a simple HTTP API. The server is distributed as a binary and, optionally, as a Docker image for cross-platform deployment. To use it, start the server via your preferred method (binary or Docker) and send HTTP requests to the exposed endpoints to perform OCR on images, obtain probability-based results, or leverage additional features such as region detection and captcha-related helpers. Typical usage involves hitting endpoints for classification, detection, and other OCR-related actions contained within the ocr_api_server functionality described in the project, with responses returning the recognized text and related metadata.

How to install

Prerequisites

Docker (recommended for quick start) or a Rust toolchain if building from source
Basic command-line knowledge

Option A: Run via Docker (recommended)

Ensure Docker is installed and running
Pull and run the image: docker run -i 86maid/ddddocr
By default the server will listen on port 8080 inside the container. Map to a host port if needed: docker run -p 8080:8080 -i 86maid/ddddocr

Option B: Build from source (Rust)

Install Rust and Cargo from https://www.rust-lang.org/tools/install
Clone the repository: git clone https://github.com/86maid/ddddocr.git
Build the binary: cd dddocr && cargo build --release
Run the server: ./target/release/ocr_api_server

Prerequisites recap

Docker for turnkey deployment or Rust toolchain for building from source
Basic network access to run and test HTTP requests against the server

Additional notes

Tips and notes:

If you encounter port conflicts, adjust the host port when using Docker (e.g., -p 8080:8080).
The server is described as not depending on OpenCV, which helps with simpler deployment across platforms.
When using Docker, ensure the image tag is up-to-date (86maid/ddddocr) and consult the project for the latest instructions.
For troubleshooting, check logs and ensure the listening port is accessible from your client environment.
If you need to customize behavior (e.g., additional models or parameters), refer to the underlying ocr_api_server implementation in the Rust source.