Ping++ MCP for AI. Unified multi-channel payment processing, period.

Q: How do I list charges using the createcharge tool?

listcharges is the correct tool for seeing history. You use it to get a general record of all transactions, while createcharge only initiates a new payment.

Q: Can I use retrievecustomer to check if a payment was successful?

No. retrievecustomer only gives profile data (like saved methods). For transaction status, you must use retrievecharge with the specific charge ID.

Q: How do I process refunds using the createrefund tool?

You need a valid charge ID. The agent runs createrefund(chargeid=...). Ping++ then submits the refund request to the correct payment channel for processing.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Ping++ is a multi-channel payment aggregator for AI agents. It lets your agent manage payments across WeChat Pay, Alipay, and UnionPay using one API endpoint.

You can create charges, process refunds, list customer accounts, and track transactions without needing dozens of separate gateway integrations.

What your AI can do

Create charge

Initiates a new payment request using required details like order number, amount, and channel type.

Create customer

Adds a brand-new customer record to the Ping++ system for tracking purposes.

Create refund

Processes and submits a refund request against an existing charge ID.

+ 4 more capabilities included

Process Payments

Use create_charge to request payments using specified order IDs and amounts across supported payment channels.

Manage Customers

Create new customer profiles or list existing ones using create_customer, list_customers, and retrieve_customer.

Handle Refunds

Process refunds for specific charges with the create_refund tool, regardless of which payment channel was used.

Track Transactions

List or retrieve detailed information on past and pending payments using list_charges and retrieve_charge.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Ping++ MCP Server: 7 Tools for Payments & Billing

These tools let your agent create payments, manage customer profiles, track history, and issue refunds across multiple payment channels.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Ping++ on Vinkius

Create Charge

Initiates a new payment request using required details like order number, amount, and channel type.

Create Customer

Adds a brand-new customer record to the Ping++ system for tracking purposes.

Create Refund

Processes and submits a refund request against an existing charge ID.

List Charges

Fetches a paginated list of all charges associated with your account.

List Customers

Retrieves a list of all customer profiles stored in the system.

Retrieve Charge

Gets specific, detailed information about one existing charge using its ID.

Retrieve Customer

Retrieves the full profile details for a single customer by their ID.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Ping++ integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "ping": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Ping++ tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"ping": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Ping++, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Ping++. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Dealing with multi-channel payments shouldn't require a dozen different API keys.

Right now, if you run an e-commerce site in China, every payment channel—WeChat, Alipay, UnionPay—demands its own dedicated integration. You have to build specific logic for how each gateway handles failure codes or refunds. Your code base becomes a mess of point-to-point API calls.

With Ping++, your agent interacts with one single MCP endpoint. You call `create_charge`, and the server figure out which payment network is best, handling all the messy routing underneath. It just works.

The create_refund tool gives you control over money movements.

Before this, if a customer demanded a refund, your dev team had to figure out which specific gateway API was responsible for the original charge and then write bespoke code just to reverse it. It took time, testing, and specialized knowledge.

Now, you simply run `create_refund` with the originating charge ID. The agent submits the request; Ping++ handles the complex communication with the downstream payment channels. Done.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

You're dealing with payments across China—WeChat Pay, Alipay, UnionPay—and you don't want your agent talking to three different backends. Ping++ gives your AI client one endpoint for all that complexity. It lets your agent handle the full payment lifecycle: starting a charge, tracking it down later, and issuing refunds, all without needing dozens of specific gateway integrations.

You focus on the business logic; we handle the network plumbing.

When you need to process payments, you'll use create_charge to initiate a new request. Just toss in the required order number, the amount, and the payment channel type. It kicks off the transaction right away. If you later need detailed info on that specific charge—maybe verifying if it went through or what the status is—you pull up those details using retrieve_charge with just its ID.

Need to see everything that's happened over the last few days? You hit up list_charges; this gives you a paginated list of all charges tied to your account, so you can sort through every transaction without running into limits.

Managing customers is just as important. If you get a brand-new buyer, you run create_customer to log them right into the Ping++ system for proper tracking. You can always check out what records you've got with list_customers, which gives you an overview of every profile stored. When your agent needs all the deep details on one specific person, they use retrieve_customer and just provide the customer ID.

It pulls the full profile history.

Handling money coming back is simple too. If a charge needs to be reversed for any reason, you don't care which payment channel was used originally; you just run create_refund. You submit that refund request using an existing charge ID, and it processes the return regardless of how the original funds moved.

This setup lets your agent manage every aspect of a transaction flow. It covers everything from initial payments to refunds, all while keeping track of who's buying what. The ability to list charges or retrieve customer profiles means you always have full visibility into past and pending transactions. You don't gotta juggle multiple APIs; it's all under one roof.

This makes running e-commerce operations or financial services in China way cleaner. Your agent just talks to the MCP server, and we make sure the money moves across WeChat Pay, Alipay, and UnionPay smoothly.

Built · Hosted · Managed by Vinkius Ping++ MCP Server - Unified Payment Operations

Server ID 019d846c-52a7-7218-98b2-35787951a575

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is, it lets your AI client treat multiple payment systems like one unified service layer.

Subscribe to the Ping++ server and grab your Secret API Key from the developer dashboard.

Inject the server into your AI client. Your agent now sees all 7 payment tools available.

Instruct your agent: 'Create a refund of 100 CNY for charge ID ch_xyz.' The agent executes create_refund and reports the status back to you.

Who is this actually for?

This server is for developers building e-commerce or financial tools that operate in China. You're the dev who needs to process payments across WeChat, Alipay, and UnionPay without writing three separate integration backends. You need one API call that handles all the mess.

E-Commerce Backend Developer

Manages checkout flows. They use create_charge to process sales and list_charges to reconcile daily revenue reports.

Financial Operations Analyst

Handles accounts reconciliation. They use retrieve_customer and list_customers to validate payment sources before processing refunds with create_refund.

DevOps Engineer (China Market)

Builds prototypes for monetization. They connect the server's tools into a single MCP endpoint to quickly test cross-channel billing flows.

What Changes When You Connect

One API for all payments. Stop building separate integrations for WeChat Pay, Alipay, and UnionPay. Ping++ lets your agent manage them through a single interface.

Full refund control. Don't need to learn specific gateway APIs to reverse money. Just use create_refund on the charge ID, and we handle the rest.

Customer data consolidation. Use list_customers or retrieve_customer to track profiles and saved payment methods across multiple channels in one place.

Comprehensive billing visibility. The list_charges tool gives you a history of every transaction—successful, failed, pending—across all connected networks.

Charge creation is simple. create_charge handles the complex initial request flow, taking required inputs like order number and amount to initiate payment.

See it in action

01 01

Handling a Failed Order

A user's payment fails on WeChat Pay. Your agent runs retrieve_charge first to get the error code, then uses that context to ask the user for an alternate method. Finally, it calls create_charge again with the new details, solving the billing failure in three steps.

02 02

Auditing Revenue Streams

You need to report on all revenue from last week. Instead of logging into multiple merchant dashboards, your agent runs list_charges. This pulls a consolidated list and identifies which channels (Alipay vs. UnionPay) contributed the most money.

03 03

Customer Onboarding

A new user signs up. Your agent first calls create_customer to establish their profile, then uses that ID when running create_charge. This ensures all future payments are correctly bound to a tracked account.

04 04

Batch Reconciliation

The finance team needs to verify 50 customer accounts. Instead of logging in individually, the agent runs list_customers, gets the IDs, and then uses those IDs with retrieve_customer to pull all necessary billing details for reconciliation.

The honest tradeoffs

Direct Gateway Calls

Anti-pattern

Trying to process a payment by calling three different SDKs: one for WeChat, one for Alipay, and one for UnionPay. This requires managing three sets of API keys and error handling logic.

The Fix

Use the create_charge tool. You pass all the necessary details (amount, order ID, etc.) to a single MCP endpoint. Ping++ handles routing the request correctly.

Ignoring Customer Context

Anti-pattern

Creating a charge without first ensuring the customer record exists. This leads to ambiguous transaction states and difficulty when running create_refund later.

The Fix

Always start by checking or creating the user profile using create_customer. Then use that verified ID when you call create_charge.

Manual Reconciliation

Anti-pattern

Exporting CSVs from multiple payment portals and trying to merge them in Excel. This is slow, error-prone, and leaves you vulnerable to data discrepancies.

The Fix

Use list_charges. It pulls a unified view of all transactions into your agent's context, making reconciliation instant.

When It Fits, When It Doesn't

You use this server if your core business logic involves accepting or issuing payments across multiple major Chinese financial networks (WeChat Pay, Alipay, UnionPay). The strength here is unification: you treat the complex payment plumbing as one service. Don't use it just because you need to list customers; other general identity services might work for that. But if your pain point is 'how do I process money in China?', this is what you need. It handles create_charge, create_refund, and customer records (create_customer) all under one roof, which saves massive amounts of integration time.

Questions you might have

How do I list charges using the create_charge tool? +

list_charges is the correct tool for seeing history. You use it to get a general record of all transactions, while create_charge only initiates a new payment.

Is Ping++ better than integrating Alipay and WeChat Pay separately? +

Yes. Using Ping++ means you connect your agent once. It unifies the management layer, so you don't write redundant code for different gateways.

Can I use retrieve_customer to check if a payment was successful? +

No. retrieve_customer only gives profile data (like saved methods). For transaction status, you must use retrieve_charge with the specific charge ID.

How do I process refunds using the create_refund tool? +

You need a valid charge ID. The agent runs create_refund(charge_id=...). Ping++ then submits the refund request to the correct payment channel for processing.

What specific data must I provide when calling the `create_charge` tool? +

You must supply several core parameters, including the order number, amount, and payment channel. The API requires these fields to categorize the charge correctly across all supported networks.

If I use `retrieve_charge`, how do I determine why a payment failed? +

The response status code tells you the failure reason immediately. Look for specific error codes in the body that detail if the issue was insufficient funds, an invalid order ID, or network refusal.

How do I authenticate my AI client when using `list_charges`? +

You use your secret API key, which you get from the developer dashboard. Pass this key in the request header for every call to validate access and maintain system security.

How often should I run `list_customers` for proper customer synchronization? +

You should run this tool periodically—maybe nightly or before a large batch of operations. This keeps your agent's view of customer profiles current and accurate across all platforms.

Which API Key do I use? +

You must use your Secret Key (Live or Test mode). Do not use the Publishable Key as it lacks permission to perform backend actions across the Ping++ network.

How do payment channels differ? +

Each channel (e.g. alipay_web, wx_pub, upacp) corresponds to a specific environment (Web, WeChat Official Account, UnionPay App). Provide the appropriate channel string when creating a charge.

Does this handle RSA Signatures automatically? +

For core operations covered by the standard MCP, API keys are sufficient. Operations requiring dedicated RSA enterprise signing may need custom webhook verifications.

Connect to your AI in seconds.

Create charge

Create customer

Create refund

Ping++ MCP Server: 7 Tools for Payments & Billing

Make your AI actually useful.

Create Charge

Create Customer

Create Refund

List Charges

List Customers

Retrieve Charge

Retrieve Customer

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Dealing with multi-channel payments shouldn't require a dozen different API keys.

The create_refund tool gives you control over money movements.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Handling a Failed Order

Auditing Revenue Streams

Customer Onboarding

Batch Reconciliation

The honest tradeoffs

Direct Gateway Calls

Ignoring Customer Context

Manual Reconciliation

When It Fits, When It Doesn't

Questions you might have