Pop Pay runs on your own machine — the client starts it, so there is no endpoint to ping. 119 installs a week from npm. Last commit 7 Jul 2026.
Runtime security for AI agent commerce. CLI + MCP server blocks hallucinated purchases.
We read the source, 23 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const found = execSync(`which ${name}`, { encoding: "utf8" }).trim();
const fullPath = path.join(__dirname, "..", "dashboard", filePath);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pop-pay -- npx -y pop-pay
{
"mcpServers": {
"pop-pay": {
"args": [
"-y",
"pop-pay"
],
"command": "npx"
}
}
}
[mcp_servers.pop-pay]
command = "npx"
args = ["-y", "pop-pay"]
{
"mcpServers": {
"pop-pay": {
"args": [
"-y",
"pop-pay"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"pop-pay": {
"args": [
"-y",
"pop-pay"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
POP_CDP_URL (Chrome DevTools Protocol endpoint for credential injection (default: http://localhost:9222)), POP_ALLOWED_CATEGORIES (JSON array of allowed vendor categories (e.g. '["aws","cloudflare"]')), POP_MAX_PER_TX (Per-transaction spending limit in USD), POP_MAX_DAILY (Daily spending limit in USD), POP_GUARDRAIL_ENGINE (Guardrail engine: 'keyword' (offline, default) or 'llm' (requires API key)).
The author declared them in the registry entry; get the values from the project itself.
Security scanner and runtime proxy for MCP servers.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Runtime proxy for MCP security, cost governance & audit
An MCP server for Arcjet - the runtime security platform that ships with your AI code.
Security scanner for AI agent skills and MCP servers
Veridion Nexus MCP server - GDPR Art. 44-49 runtime compliance for AI agents
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Answers built from our own checks of this server.