Log inSubmit server
Omni Lpr logo

Omni Lpr

Expose license plate detection and OCR to MCP clients through local images, URLs, file paths, or image data.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Omni Lpr

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "omni-lpr": {
      "command": "uvx",
      "args": [
        "omni-lpr"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The omni-lpr MCP server provides license plate detection and optical character recognition tools for AI agents. It runs as a self-hosted Python service and exposes the tools over streamable HTTP at the `/mcp/` endpoint. Agents can list available models, process image data, or submit a URL or local file path. Reach for it when an MCP client needs to inspect license plates without embedding the recognition stack in the client application.

Use cases

  • Inspect license plates in uploaded images
  • Read plates from URLs or local files
  • Detect multiple plates in a full image
  • List the detector and OCR models
  • Connect an AI agent to a self-hosted ALPR service

Key features

  • Streamable HTTP MCP endpoint
  • License plate detection and OCR
  • Image-data and path-based tools
  • Detector and OCR model listing
  • REST API with Swagger documentation
  • CPU, OpenVINO, and CUDA Docker images

Tools5

What Omni Lpr lets your agent do. Expand a tool for its parameters.

Self-reported~101 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

8/8 checks healthy over the last 41d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · omni-lpr (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars26Stargazers on the source repository.
Last commit3mo agoMost recent push to the default branch.
Tools exposed5Callable tools this server registers over MCP.

How Omni Lpr works

What omni-lpr does

The omni-lpr MCP server exposes automatic license plate recognition through the Model Context Protocol. It can read plate text from an image that has already been cropped, or find and read all plates in a larger image. Inputs can be supplied as image data or as a URL or local file path, depending on the tool used.

The service is self-hosted and can also function as a standalone REST service. For MCP clients, its tools are available from a streamable HTTP endpoint. This makes it suitable for agent workflows that need to inspect submitted images while keeping the Python and machine-learning dependencies in a separate service.

How it works

Install the package, start the server, and connect an MCP client to http://127.0.0.1:8000/mcp/. The server listens locally on port 8000 by default. An MCP client can then discover the available tools and invoke them through the protocol.

The processing path depends on the input:

  • Use image-data tools when the client has a Base64 image or file upload.
  • Use path-based tools when the image is available through a URL or local filesystem path.
  • Use the detection-and-recognition tools for full images that may contain one or more plates.
  • Use the recognition-only tools when the supplied image is already cropped to a plate.

The server includes detector and OCR models, and list_models reports which models are available.

Setup and configuration

Install the Python package with pip install omni-lpr, then run omni-lpr. A health endpoint at /api/health can confirm that the service is running. The REST API exposes the same tool operations below the /api/v1 prefix, with interactive Swagger documentation available at /api/v1/apidoc/swagger.

For an MCP client, configure the streamable HTTP URL rather than a command-based stdio launch. The README demonstrates this setup with LM Studio using http://127.0.0.1:8000/mcp/. MCP Inspector can also be used to explore the exposed tools.

Tools and capabilities

The omni-lpr MCP server provides these five tools:

  • list_models lists the available detector and OCR models.
  • recognize_plate reads text from a pre-cropped plate image supplied as image data.
  • detect_and_recognize_plate locates and reads all plates in a full image supplied as image data.
  • recognize_plate_from_path reads text from a pre-cropped plate image at a URL or local path.
  • detect_and_recognize_plate_from_path locates and reads plates in a full image at a URL or local path.

Limitations and notes

The project is described as being in early development, so breaking API changes and bugs may occur. It also does not establish accuracy, supported plate regions, or image-size requirements. Review the project documentation before exposing the service beyond a trusted environment.

Hardware-specific Docker images are available, but choosing CPU, OpenVINO, or CUDA depends on the deployment environment.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Omni Lpr

omni-lpr is an MCP server that connects AI agents to automatic license plate recognition tools. It can list detector and OCR models, read text from cropped plate images, and detect and recognize plates in full images. Inputs can be image data, URLs, or local file paths.

Install it with `pip install omni-lpr`, then start it by running `omni-lpr`. The service listens on `http://127.0.0.1:8000` by default, and its MCP endpoint is available at `http://127.0.0.1:8000/mcp/`.

Yes, omni-lpr works with LM Studio through its streamable HTTP MCP endpoint. Add a server entry using the URL `http://127.0.0.1:8000/mcp/` after starting the local omni-lpr service.

Yes, omni-lpr supports URL and local path inputs with `recognize_plate_from_path` for cropped plates and `detect_and_recognize_plate_from_path` for full images. Image-data alternatives are available through the corresponding non-path tools.

Related MCP servers

All in Developer Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOmni Lpr AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/omni-lpr?style=directory)](https://allmcps.com/mcp/omni-lpr)
HTML Embed
<a href="https://allmcps.com/mcp/omni-lpr"><img src="https://allmcps.com/api/badge/omni-lpr?style=directory" alt="Omni Lpr on AllMCPs" /></a>