Is Uganda Payments MCP stateless?
Yes, it is a stateless translation layer. Funds flow directly from buyer to Flutterwave to merchant; the server never holds funds or stores credentials. It has no database.
@junter1989k-ai
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"uganda-payments": {
"type": "http",
"url": "https://mcp-ug.wishpool.app/mcp"
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
Uganda Payments MCP is a remote MCP server that lets any AI agent (Claude, ChatGPT, Cursor) accept payments in Uganda via MTN Mobile Money, Airtel Money, or cards, powered by Flutterwave’s hosted checkout. It is designed for developers building AI‑powered payment flows in Uganda.
Connect your MCP client to the endpoint https://mcp-ug.wishpool.app/mcp over Streamable HTTP. Supply your Flutterwave secret key as the x-flutterwave-secret-key header (test mode: FLWSECK_TEST-…, production: FLWSECK-…). Use the provided tools create_payment_link and query_payment_status to create UGX checkout links and check payment status.
Yes, it is a stateless translation layer. Funds flow directly from buyer to Flutterwave to merchant; the server never holds funds or stores credentials. It has no database.
From a developer perspective, only Node.js ≥ 18 is needed for local testing or contribution. The public MCP endpoint requires no server‑side setup.
The MCP server authenticates requests via the `x-flutterwave-secret-key` header, which must contain a valid Flutterwave secret key (test or production). No other authentication is needed.
It uses Streamable HTTP with stateless JSON‑RPC. The endpoint is `https://mcp-ug.wishpool.app/mcp`.
Uganda Payments MCP acts as an MCP server so that AI agents can create and check payments without custom integration code. It only exposes two tools (`create_payment_link` and `query_payment_status`) and never stores credentials or funds.

Google Gemini MCP - Use Google's visual, video and chat capabilities in your AI Assistant. Uses MCP Apps to preview created images, landing pages, SVGs and video
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.
コメント