Agentpay runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from npm.
Spending controls for AI agents: per-agent budgets, vendor allowlists, full audit trail.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 agentpay -e 'AGENTPAY_API_KEY=<AGENTPAY_API_KEY>' -- npx -y @agentpay-run/mcp-server
{
"mcpServers": {
"agentpay": {
"command": "npx",
"args": [
"-y",
"@agentpay-run/mcp-server"
],
"env": {
"AGENTPAY_API_KEY": "<AGENTPAY_API_KEY>"
}
}
}
}
[mcp_servers.agentpay]
command = "npx"
args = ["-y", "@agentpay-run/mcp-server"]
env = { AGENTPAY_API_KEY = "<AGENTPAY_API_KEY>" }
{
"mcpServers": {
"agentpay": {
"command": "npx",
"args": [
"-y",
"@agentpay-run/mcp-server"
],
"env": {
"AGENTPAY_API_KEY": "<AGENTPAY_API_KEY>"
}
}
}
}
{
"servers": {
"agentpay": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agentpay-run/mcp-server"
],
"env": {
"AGENTPAY_API_KEY": "<AGENTPAY_API_KEY>"
}
}
}
}
Put your own value in place of
<AGENTPAY_API_KEY> (AgentPay wallet API key (ap_test_... or ap_live_...). Generate at https://agentpay.run/dashboard).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
AGENTPAY_BASE_URL (Override for self-hosted or local dev. Defaults to https://agentpay.run).
Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.
Budget, payment and audit controls for AI agent API calls and MCP tool calls.
Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.
AI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs
Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.
Budgets, payee allowlists, price-spike checks and human approval for agents paying x402 paywalls
Task and sprint coordination for humans and AI agents, with scoped API keys and full audit trail.
Governance layer for AI coding agents: knowledge-graph grounding, session audit, policy controls.
Answers built from our own checks of this server.