About AgentPay VN
AgentPay VN provides VietQR payment infrastructure for AI agents, aimed at merchants and bot developers collecting payments in conversations. It creates payment QR codes and monitors bank transactions to confirm settlement; funds go directly to the merchant, never through the platform.
Key features
- 01Create VietQR payment requests and checkout links
- 02Poll payment status until settlement
- 03Send payment events through webhooks
- 04Use sandbox keys and simulated settlements
- 05Use synchronous and asynchronous Python SDKs
Use cases
- 01Send a QR code or payment link in chat
- 02Release goods or services after confirmed payment
- 03Test a payment flow in the sandbox
- 04Receive and verify settlement webhooks
MCP support
The MCP server exposes tools to register a sandbox key, create payment requests, check payments, await settlement, and list recent payments.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx agentpay-vnAGENTPAY_API_KEYSecretAgentPay API key (ap_live_* or ap_test_*). Optional — call the register_sandbox tool to self-issue a free sandbox key.AGENTPAY_BASE_URLAPI base URL.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAgentPay VN
VietQR payment infrastructure for AI agents — collect money inside any conversation.
AgentPay VN lets AI agents (Claude, GPT, custom bots) generate payment QR codes, send them to users, and automatically confirm when the money arrives — all without ever holding or touching funds. Money flows directly from the payer's bank account into the merchant's account; AgentPay only reads the bank transaction feed to confirm settlement.
Status: Early access / self-hosted — running on the same swarm as Sổ Nợ AI.
How it works
AI Agent AgentPay API Bank feed (SePay)
| | |
|-- create_payment_request ->| |
|<- { qr_image_url, id } ----| |
| | |
|-- send QR to user -------->| |
| | user scans & pays |
| |<-- webhook (bank txn) ----|
| |-- match AP* pay_code |
| |-- status → settled |
|<-- await_settlement done --| |
| | |
|-- deliver order / unlock ->| |
- Create — agent calls
POST /v1/payment-requests→ gets a VietQR image URL and a checkout page. - Send — agent embeds the QR image or sends the checkout link to the user in chat.
- Await — agent calls
await_settlement()(or the MCP tool) to poll untilstatus = settled. - Deliver — only after confirmed settlement does the agent release the goods/service.
AgentPay never holds money. The QR points directly at the merchant's bank account number. The platform only monitors the bank transaction feed to detect matching transfers.
Quick start
1. Install
pip install agentpay-vn
2. Get an API key — no account needed
A sandbox key is self-serve and instant:
curl -X POST https://agentpay.servicesai.vn/v1/sandbox/register \
-H "Content-Type: application/json" -d '{"shop_name": "My Bot"}'
# -> { "api_key": "ap_test_...", "expires_at": "..." }
export AGENTPAY_API_KEY=ap_test_xxx
From Python: register_sandbox(). From an agent: just call the register_sandbox
MCP tool — it issues the key and applies it to the session.
Sandbox keys last 7 days, move no real money, and renew by calling the same endpoint
with the same email. For real payments you need an ap_live_* key, which requires a
registered merchant with a Vietnamese bank account — sign up at
agentpay.servicesai.vn.
3. Collect a payment (3 lines)
from agentpay.client import AsyncAgentPayClient, await_settlement
import asyncio
async def main():
async with AsyncAgentPayClient("ap_test_xxx") as client:
pr = await client.create_payment_request(amount=50_000, description="Order #1")
print(pr["checkout_url"]) # send this link to your user
result = await await_settlement(client, pr["id"], timeout=120)
assert result["status"] == "settled"
asyncio.run(main())
See examples/quickstart.py for the full runnable version.
MCP server setup
AgentPay ships an MCP server so any MCP-compatible AI agent can call it as a tool — no extra code needed.
Claude Desktop / Claude Code
Add to claude_desktop_config.json (or use examples/claude_desktop_config.json):
{
"mcpServers": {
"agentpay": {
"command": "python",
"args": ["-m", "agentpay.mcp_server"],
"env": {
"AGENTPAY_API_KEY": "ap_test_xxx",
"AGENTPAY_BASE_URL": "https://agentpay.servicesai.vn/v1"
}
}
}
}
Or use the installed console script:
{
"mcpServers": {
"agentpay": {
"command": "agentpay-mcp",
"env": { "AGENTPAY_API_KEY": "ap_live_xxx" }
}
}
}
Available MCP tools
| Tool | Description |
|---|---|
register_sandbox | Self-issue a free ap_test_* key — call this first when no key is set |
create_payment_request | Generate a VietQR code for a given amount |
check_payment | Get current status of a payment request |
await_settlement | Poll until payment arrives or timeout (max 600 s) |
list_recent_payments | List last N settled transactions |
Agent skill (Claude Code, Cursor, and other agents)
The MCP server gives an agent the tools. The bundled skill gives it the judgement:
when to charge, how to format a VND amount, and the rule that nothing ships before
status = settled. See skills/agentpay-vn/SKILL.md.
This repository is also a Claude Code plugin marketplace, so the skill and the MCP server install together in one step:
claude plugin marketplace add phuocdu/agentpay-vn
claude plugin install agentpay-vn@agentpay-vn
Claude Code prompts for your API key (stored in the OS credential store, not in
settings.json). Leave it blank to start in sandbox — the agent will call
register_sandbox on its first charge.
For other agents, copy skills/agentpay-vn/ into wherever that agent reads skills from,
and add the MCP server as shown above.
Python SDK
Synchronous
from agentpay.client import AgentPayClient
with AgentPayClient("ap_live_xxx") as client:
# Create
pr = client.create_payment_request(
amount=150_000,
description="Consulting session 30 min",
ttl_minutes=30,
idempotency_key="session-abc-123",
)
# Poll manually
import time
for _ in range(60):
pr = client.get_payment_request(pr["id"])
if pr["status"] != "pending":
break
time.sleep(5)
# Reconcile
txns = client.list_transactions(limit=10)
Asynchronous
from agentpay.client import AsyncAgentPayClient, await_settlement
async with AsyncAgentPayClient("ap_live_xxx") as client:
pr = await client.create_payment_request(amount=75_000, description="eBook download")
result = await await_settlement(client, pr["id"], timeout=300)
if result["status"] == "settled":
send_download_link(result["metadata"].get("email"))
Webhook verification
import hashlib, hmac
def verify_webhook(raw_body: bytes, signature_header: str, secret: str) -> bool:
expected = hmac.new(secret.encode(), raw_body, hashlib.sha256).hexdigest()
return hmac.compare_digest(expected, signature_header)
Register a webhook endpoint:
ep = client.register_webhook(
url="https://your-server.com/webhooks/agentpay",
events=["payment.settled", "payment.expired"],
)
print(ep["secret"]) # store this — shown only once
API reference
- OpenAPI spec:
agentpay-openapi.yaml - Base URL:
https://agentpay.servicesai.vn/v1 - Authentication:
Authorization: Bearer ap_live_xxx(orap_test_xxxfor sandbox)
Key endpoints
| Method | Path | Description |
|---|---|---|
POST | /v1/payment-requests | Create payment request |
GET | /v1/payment-requests/{id} | Get status |
POST | /v1/payment-requests/{id}/cancel | Cancel pending request |
GET | /v1/transactions | List settled transactions |
POST | /v1/webhook-endpoints | Register webhook URL |
POST | /v1/sandbox/simulate-settlement | Simulate payment (sandbox only) |
GET | /pay/{pay_code} | Public checkout page (HTML, mobile-friendly) |
Self-hosting
AgentPay runs as part of the Sổ Nợ AI FastAPI backend.
Requirements
- Docker Swarm cluster (same as Sono)
- MongoDB (shared with Sono)
- SePay bank feed account (for live payments)
- Nginx with an
agentpay.servicesai.vnvhost
Environment variables
| Variable | Default | Description |
|---|---|---|
AGENTPAY_BASE_URL | https://agentpay.servicesai.vn | Public base URL for checkout links |
MONGO_URI | mongodb://localhost:27017 | Inherited from Sono |
BILLING_WEBHOOK_TOKEN | — | SePay webhook token (inherited) |
Create an API key (admin)
curl -X POST https://sono.servicesai.vn/api/admin/agentpay/keys \
-H "Authorization: Bearer <admin-jwt>" \
-H "Content-Type: application/json" \
-d '{"org_id": "<shop-user-id>", "name": "My bot", "livemode": true}'
The response includes the full key — store it immediately; it is shown only once.
Rate limits
| Tier | Settled payments/month | Requests/minute |
|---|---|---|
| Free | 50 | 120 |
Design principles
-
No money held — QR codes point directly at the merchant's bank account. AgentPay only reads the transaction feed; it never touches the money.
-
Idempotency — pass an
Idempotency-Keyheader onPOST /payment-requeststo safely retry without creating duplicates (24-hour deduplication window). -
HMAC webhook verification — every outbound webhook is signed with
HMAC-SHA256(whsec_..., raw_body)in theAgentPay-Signatureheader. Always verify before processing. -
Sandbox — use
ap_test_*keys andPOST /v1/sandbox/simulate-settlementto develop and test without real transactions. -
Minimal trust surface — the MCP server is a thin REST client with no local secrets beyond the API key. Compromising an agent key only exposes one tenant's payment-request creation ability.
License
MIT © 2026 ServicesAI — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.