SSE-based Server and mobile Angular App
About
MCP server for image recognition with Angular mobile client app.
Explore
- SSE‑based MCP server for cloud‑native deployments
- Image recognition using OpenAI or local Ollama models
- Streamlit client app for desktop interaction
- Mobile Angular app built with Capacitor for iOS
- Docker support for hosting the MCP server
- Configurable system and user prompts for recognition
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
SSE-based Server and mobile Angular AppCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the required packages and the MCP server and client:
sudo apt install nodejs npm
brew install nodejs npm
conda install -c conda-forge mcp
conda env create -f environment.yml
conda activate imagerecog
python -m pip install "mcp[cli]"
mcp dev src/server.py
python src/server.py
python -m streamlit run mobile/app.py
ollama run llama3.2-vision
npm install -g @angular/cli
npm install
ng serve
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"sse-based server and mobile angular app": {
"imagerecog": {
"command": "python",
"args": [
"-m",
"pip",
"install",
"mcp[cli]"
]
}
}
}
}McpServers
{
"imagerecog": {
"command": "python",
"args": [
"-m",
"pip",
"install",
"mcp[cli]"
]
}
}Image recognition tool on top of the MCP protocol. This project is designed to provide a simple and efficient way to recognize images using a server-client architecture.
Why?
MCP server can now be some running process that agents (clients) connect to, use, and disconnect from whenever and wherever they want. In other words, an SSE-based server and clients can be decoupled processes (potentially even, on decoupled nodes). This is different and better fits "cloud-native" use-cases compared to the STDIO-based pattern where the client itself spawns the server as a subprocess.
Setup
Install the required packages and the MCP server and client:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
