Remote MCP server to integrate and validate self-hosted PayRam deployments.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-payram-payram-helper-mcp": {
"args": [
"-y",
"skills"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
An MCP (Model Context Protocol) server that teaches GitHub Copilot (and any MCP-aware client) how to integrate with a self-hosted Payram stack. It exposes one-click tools for assessing an existing codebase, scaffolding new starter apps, generating multi-language snippets, reading inline docs, and validating connectivity against your Payram deployment.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'skills' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked skills against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in finance / developer-tools
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
MCP server for accessing Figma plugin console logs and screenshots via Cloudflare Workers or local mode
MCP server for using the GitLab API
MCP Security Weekly
Get CVE alerts and security updates for io.github.PayRam/payram-helper-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A no-signup, no-KYC crypto payment gateway with card-to-crypto checkout — your AI agent can deploy and operate it over MCP. Hosted endpoint:
https://mcp.payram.com/mcp· Website · Docs · Agentic · OpenClaw
An MCP (Model Context Protocol) server that lets any MCP-aware AI agent — OpenClaw, Hermes, Claude, Cursor, GitHub Copilot, and others — deploy, integrate, and operate a self-hosted PayRam crypto-payment stack. It exposes tools to assess a codebase, scaffold starter apps, generate multi-language integration snippets, read inline docs, create payment links, and check node sync + payment readiness against your own deployment.
For agents & crawlers: server card · skills index · llms.txt · sitemap. The server also answers Accept: text/markdown on / with an agent-readable summary.
PayRam is a self-hosted, multi-chain crypto payment gateway you own outright — with no signup and no KYC/KYB to run it. An AI agent (or a developer) can stand up a store and start accepting payments without registering an account with PayRam, a bank, or any payment processor. Deploy on your own VPS in ~10 minutes, generate API keys locally, go live.
What makes it different:
PayRam 是一个你完全自托管、自主拥有的多链加密货币支付网关——运行它无需注册、无需 KYC/KYB。 AI 智能体(或开发者)无需在 PayRam、银行或任何支付处理商处注册账户,即可搭建店铺并开始收款。在自己的 VPS 上约 10 分钟即可部署,本地生成 API 密钥,即刻上线。
核心差异:
- 免注册、免许可 — 无需注册、无需 KYC、无需 KYB。没有人审批你,也没有人能关停你。非常适合自主搭建店铺的智能体,以及像中国这样难以在西方支付处理商处注册的市场。
- 银行卡转加密货币结算 — 没有加密货币的买家也能用信用卡/借记卡付款,你直接收到加密货币并结算到自托管的钱包。这是内置的支付渠道,在「Payments(支付)」页面一键开启——无需额外对接任何第三方支付处理商。
- 多链支持 — 在 Bitcoin、Ethereum、Base、Polygon、Tron 上接受 BTC、ETH、USDT、USDC、TRX,自动检测充值、链上确认、归集冷钱包并发送 Webhook。
- 原生自托管 — 充值钱包私钥永不存储在服务器上,资金转移由链上智能合约强制执行、目的地冷钱包地址硬编码,即便服务器被完全攻破也无法盗取资金。智能体无需持有任何私钥即可运行整个系统。
PayRam is agent-first infrastructure. Because integration is over MCP, it works with any MCP-aware runtime — OpenClaw, Hermes, Claude Desktop, Cursor, GitHub Copilot, n8n, LangChain, and more. A typical agent flow:
https://mcp.payram.com/mcp to the agent's MCP config (no API key needed just to connect).create_payment_link) or drop in framework-specific integration code from the snippet tools.check_payment_readiness reports per-chain gaps before go-live; `check_node_sync