
Omni Lpr
This server wraps automatic license plate recognition into both REST and MCP interfaces, letting you detect and read plates from images without embedding Python ML dependencies into your application. It exposes tools like detect_and_recognize_plate_from_path that take image URLs or local paths, plus variants that work with base64 encoded data or file uploads. The recognition pipeline handles both detection and OCR, with support for CPU (ONNX), Intel OpenVINO, and CUDA acceleration. You'd reach for this when building applications that need ALPR capabilities but want to keep the ML stack isolated in a separate service, or when connecting LLMs to computer vision tasks through the MCP protocol.
- GitHub stars
- 26
- tools
- 5
- transport
- HTTP
- last updated
- Jul 5, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
list_modelsLists the available detector and OCR models.
Lists the available detector and OCR models.
No parameter schema in public metadata yet.
recognize_plateRecognizes text from a pre-cropped license plate image.
Recognizes text from a pre-cropped license plate image.
No parameter schema in public metadata yet.
detect_and_recognize_plateDetects and recognizes all license plates in a full image.
Detects and recognizes all license plates in a full image.
No parameter schema in public metadata yet.
recognize_plate_from_pathRecognizes text from a pre-cropped license plate image at a given path.
Recognizes text from a pre-cropped license plate image at a given path.
No parameter schema in public metadata yet.
detect_and_recognize_plate_from_pathDetects and recognizes plates in a full image at a given path.
Detects and recognizes plates in a full image at a given path.
No parameter schema in public metadata yet.
Sponsors
Readme
Details
- Repository
- github.com/habedi/omni-lpr
- Transport
- HTTP
- Registry
- MCP registry, active