Loadingplay MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Loadingplay MCPlist my products"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Loadingplay MCP
Servidor MCP para exponer herramientas de Loadingplay mediante Streamable HTTP.
Endpoints
GET /health: health check simplePOST /mcp: endpoint MCP estandar
Nota: algunos clientes tambien pueden hacer GET /mcp durante la negociacion del transporte. El SDK MCP maneja eso internamente.
Variables de entorno
Define estas variables en Railway:
LP_BASE_URL=https://api.loadingplay.com
LP_API_KEY=tu_api_key
PORT=8000Desarrollo local
pip install -r requirements.txt
python main.pyServidor disponible en:
http://localhost:8000/healthhttp://localhost:8000/mcp
Deploy en Railway
Configura el start command con alguno de estos:
python main.pyo
uvicorn main:app --host 0.0.0.0 --port $PORTCambio importante
La version anterior exponia una API REST custom con /mcp y /mcp/call. Eso no era compatible con clientes MCP reales. Esta version usa el SDK oficial de MCP y expone un endpoint compatible para registro y ejecucion de tools.
Related MCP Connectors
Host your MCP tool over streamable HTTP in one command.
MCP server for progressive tool usage at any scale (see https://klavis.ai)