Omni-LPR

Self-hosted ALPR server with REST and MCP interfaces for license plate recognition.
  • python

19

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

Omni-LPR is a self-hosted server that delivers automatic license plate recognition capabilities through both REST and MCP interfaces. You can run it as a standalone ALPR microservice or integrate it as a toolbox for AI agents and language models, enabling scalable, language-agnostic access to license plate detection and recognition tasks.

How to use

You interact with Omni-LPR by connecting your client or AI agent to its REST API or through the MCP interface. Prefer the MCP endpoint when integrating with AI agents that rely on the MCP protocol, and use the REST endpoints for straightforward HTTP requests from any application.

How to install

# Install the server from PyPI
pip install omni-lpr

# Start the server (default address and port)
omni-lpr

# Confirm the server is healthy
curl http://127.0.0.1:8000/api/health

Configuration and usage notes

The server exposes tools that perform model listing and plate recognition either from image data or from image paths. The REST API is available under the /api/v1 prefix, and the MCP endpoint is exposed at /mcp/ for streamable communication. Use the health endpoint to verify the server is running and to check the version.

Security and troubleshooting

Run the server behind appropriate network controls and keep dependencies up to date. If you encounter issues with recognition accuracy or API changes during early development, open issues to report bugs or request features so the project can improve stability.

Examples and integration patterns

Connect your client or agent using either the REST API or MCP. For MCP-based integration, point your MCP client at the MCP URL and discover available tools. For REST-based workflows, use the documented endpoints to list models and perform recognition on images or image URLs.

Available tools and endpoints overview

The server provides a set of tools to list models, recognize text from cropped license plate images, and detect-and-recognize plates in full images. Tools are accessible via REST and MCP interfaces.

Available tools

list_models

Lists the available detector and OCR models used for license plate recognition.

recognize_plate

Recognizes text from a pre-cropped image of a license plate.

detect_and_recognize_plate

Detects all license plates in a full image and recognizes the text.

recognize_plate_from_path

Recognizes text from a pre-cropped license plate image located at a given path.

detect_and_recognize_plate_from_path

Detects and recognizes plates in a full image located at a given path.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational