How to Use the ChargeDesk MCP in LangChain

Q: How do I build a ChargeDesk refund chain in LangChain?

You give your agent the getchargedetails and refundchargedeskpayment tools. Then you define a prompt that instructs the agent to first verify the charge details before attempting a refund. LangChain's ReAct framework handles the step-by-step execution.

Q: Can my LangChain agent see all my ChargeDesk customers?

Yes, it can use the listchargedeskcustomers tool to get a list of all customers in your account. You can then chain that with getcustomerdetails to drill down into specifics for any given customer.

Q: What's the best way to handle multiple ChargeDesk gateways with LangChain?

Your agent can call listconnectedgateways to see which payment processors are active. The results from listchargedeskcharges will then include charges from all of them automatically. You don't need to write separate logic for each gateway.

Build multi-step billing workflows in LangChain. Your agents can now find a customer, check their charges, and issue a refund in one sequence.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChargeDesk MCP to LangChain

Create your Vinkius account to connect ChargeDesk to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ChargeDesk with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Billing Operations Together

Your LangChain agent can now build sequences for customer support. Instead of just fetching data, it can reason through a problem. For example, it can start by using `list_chargedesk_customers` to find a user, then `get_customer_details` to check their status, and finally `list_chargedesk_charges` to see their payment history. This isn't just a simple script. The agent decides the next step based on the previous result. If a charge looks wrong, it can be programmed to flag it for review or directly invoke `refund_chargedesk_payment` if the rules match. You're building autonomous billing logic, not just calling an API.

Build Custom Support Agents with LangChain

Connect this ChargeDesk MCP Server to your agent and give it real financial tools. Your support agent can now answer "what was my last charge?" by calling `list_chargedesk_charges` and filtering the results. It can find customer data with `get_customer_details` without you ever opening the ChargeDesk dashboard. Because LangChain lets you compose tools, you can combine these abilities. Build a chain that first finds a customer, then lists their active subscriptions with `list_chargedesk_subscriptions`, and then asks for confirmation before making a change. You're in control of the entire workflow.

Automate Refund and Dispute Logic

Go beyond simple data lookups. Give your agent the power to act. The `refund_chargedesk_payment` tool lets your agent process refunds based on predefined logic, without manual intervention. It's perfect for handling common, low-risk refund requests automatically. You can trace every step in LangSmith. See exactly why the agent decided to issue a refund, which data it checked using `get_charge_details`, and how long the entire chain took to execute. This gives you full observability into your automated billing operations.

Setup guide

Set up ChargeDesk MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ChargeDesk tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "chargedesk-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ChargeDesk transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ChargeDesk. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect ChargeDesk now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about ChargeDesk MCP in LangChain

You give your agent the `get_charge_details` and `refund_chargedesk_payment` tools. Then you define a prompt that instructs the agent to first verify the charge details before attempting a refund. LangChain's ReAct framework handles the step-by-step execution.

Yes, it can use the `list_chargedesk_customers` tool to get a list of all customers in your account. You can then chain that with `get_customer_details` to drill down into specifics for any given customer.

Your agent can call `list_connected_gateways` to see which payment processors are active. The results from `list_chargedesk_charges` will then include charges from all of them automatically. You don't need to write separate logic for each gateway.

Absolutely. That's what LangChain is for. You can create a chain where your agent first checks a charge with `get_charge_details`, then logs the result to a database or sends a Slack notification using other integrations.

Your Vinkius token authenticates your agent. All requests for ChargeDesk data, like customer names or charge amounts, are sent over encrypted HTTPS connections directly to the sandboxed MCP server. The server itself is ephemeral, meaning no data persists after the operation is complete.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript