@junter1989k-ai
基本信息
Accept payments in Japan (JPY) from any AI agent - konbini convenience store, credit card, PayPay, bank transfer - via KOMOJU hosted checkout. Stateless BYO-credentials design, never holds funds. Remote endpoint: https://mcp-jp.wishpool.app/mcp
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"japan-payments": {
"url": "https://mcp-jp.wishpool.app/mcp"
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,直接连接服务器端点实时获取工具列表。
A remote Model Context Protocol (MCP) server that lets AI agents create payment links and check payment status for Japanese payment rails — konbini (コンビニ決済), credit cards, PayPay, bank transfer, Pay-easy, LINE Pay, Merpay, au PAY, and Rakuten Pay. It works as a stateless translation layer routing through KOMOJU, a Japanese payment gateway with a hosted checkout page. The server is designed for developers building agentic applications that need to accept payments in Japan.
Add the endpoint https://mcp-jp.wishpool.app/mcp in any remote-MCP client (Claude Desktop, Claude Code, Cursor). On each request, send your KOMOJU secret key as the header x-komoju-secret-key. Two tools are available: create_payment_link (creates a JPY hosted-checkout link) and query_payment_status (checks if a session is paid).
It provides two tools for AI agents: create a Japanese hosted-checkout payment link and check whether that session has been paid (captured or authorized). Funds flow directly from buyer to merchant via KOMOJU; the server never handles money.
You need your own KOMOJU secret key. A test-mode key (`sk_test_...`) is free from the KOMOJU dashboard after switching to Test mode, and never moves real money. A production key (`sk_live_...`) is for live payments. There is no public demo key.
No. It is a stateless translation layer with no database. It never holds, moves, or stores funds, credentials, or any other sensitive data.
Call the `query_payment_status` tool with the session identifier. It returns the current status (e.g., `captured` or `authorized`). The check is pull-based — no webhook configuration is needed.
The remote endpoint is always available. For local development, you need Node.js ≥ 18. The server has zero runtime dependencies.
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
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
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
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.
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
评论