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., "@iCafeCloud MCP Show me the status of all PCs in cafe 1"
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.
A remote MCP server that wraps the iCafeCloud internet-cafe management API and plugs into claude.ai as a custom connector — so you can run your cafe from a normal Claude chat on web, desktop, or mobile.
claude.ai → Anthropic cloud → this server (VPS, static IP) → api.icafecloud.comHosting on the VPS solves iCafeCloud's IP-bound token: every upstream call originates from that one
static IP. See docs/ARCHITECTURE.md.
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
cp .env.example .env # fill in credentials
icafecloud-mcp # runs Streamable HTTP on :8080
npx @modelcontextprotocol/inspector # poke at the toolsRelated MCP server: Vast.ai MCP Server
list_pcs · pc_status · send_pc_command · get_member · revenue_report (topup_member optional).
docs/ARCHITECTURE.md — diagrams: request path, security model, modules.
docs/DEVELOPMENT_PLAN.md — SDLC flow + decomposed task backlog.
CLAUDE.md — guidance for Claude Code working in this repo.
Python 3.11+ · FastMCP · httpx · Streamable HTTP transport (SSE intentionally unused — it is being phased out).
This server cannot be deployed
Manage HepCloud (Turkish cloud) servers and managed PostgreSQL from your AI assistant. OAuth 2.1.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Run your restaurant from an AI client: orders, menu, reports, refunds, payouts and staff.
