What distinguishes this from a STDIO‑based MCP server?
SSE allows the MCP server and client to run as decoupled processes, potentially on separate nodes, fitting cloud‑native patterns better than STDIO where the client spawns a subprocess.
@DrBenjamin
Basic information
MCP server for image recognition with Angular mobile client app.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"imagerecog": {
"command": "python",
"args": [
"-m",
"pip",
"install",
"mcp[cli]"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
An image recognition tool built on the Model Context Protocol (MCP) using an SSE-based server–client architecture. It enables decoupled, cloud‑native image recognition where the MCP server runs as a separate process that agents can connect to and disconnect from on demand, unlike the traditional STDIO‑based pattern.
Install Node.js, Python, and the MCP package, then clone the repository. Run the MCP server with python src/server.py (or mcp dev src/server.py for development) and launch either the Streamlit client (python -m streamlit run mobile/app.py) or the mobile Angular app (ng serve after installing dependencies). Configure the OpenAI or Ollama API key in .streamlit/st.secrets.toml.
SSE allows the MCP server and client to run as decoupled processes, potentially on separate nodes, fitting cloud‑native patterns better than STDIO where the client spawns a subprocess.
Node.js, Python, the MCP package (via pip or conda), and either Ollama (for local models) or an OpenAI API key. For mobile, Angular CLI and Capacitor are needed.
Authentication is not built‑in; the OpenAI API key is provided via the `.streamlit/st.secrets.toml` configuration file for cloud‑based recognition.
Yes, a Dockerfile is provided. Build and push the image, then add it to a client like VS Code or Claude Desktop.
Images are sent as base64 bytes or URLs from the client to the MCP server; the server passes them to the chosen LLM (local Ollama or OpenAI) for recognition. No image storage is described.

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Painless E2E Automation for Mobile and Web

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Comments