How to Use the Getpaid MCP in LangChain

Q: How do I connect the Getpaid MCP server to LangChain?

Call MultiServerMCPClient with your Getpaid endpoint URL. Pass the resulting tool list into createagent to start building billing pipelines.

Q: Can LangChain track the latency of Getpaid tool calls?

Yes. Every call to getaccountdetails or listbillingpayments registers as a step in LangSmith. You see the exact execution time and input arguments.

Q: How do I handle persistent billing contexts in LangChain with Getpaid?

Use client.session() to maintain state across multiple interactions. This keeps customer IDs in context so you don't repeat listbillingcustomers calls.

Build automated billing chains in LangChain that handle checkout creation, invoice tracking, and refunds via Getpaid MCP Server tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Getpaid MCP to LangChain

Create your Vinkius account to connect Getpaid 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 Getpaid with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain MCP Server Pipelines

The `create_checkout_session` tool initiates the payment flow inside your LangChain agent. Your ReAct pipeline doesn't just stop at generating a link; it passes that session ID directly into a loop checking `get_checkout_status` until the transaction clears. Once the payment settles, the chain automatically hands the output to `list_billing_subscriptions`. You get a complete, traceable sequence in LangSmith showing exactly how long the checkout took and how many tokens the agent burned making the decision.

Automated Refund Logic

The `refund_billing_payment` tool executes money movement directly from your agent's decision node. You feed customer support tickets into the chain, and the agent pulls transaction metadata using `get_payment_details`. If the rules match, the agent fires the refund tool and logs the state change. You don't write custom API wrappers for Getpaid; the MCP adapter translates the schema, letting the agent chain execute the return instantly.

Customer Data Retrieval

The `get_customer_details` tool feeds live user profiles into your prompt templates. When a user asks about their billing history, the agent calls `list_billing_invoices` and formats the array into a readable summary. You bind these tools directly to the LLM using the standard LangChain interface. The agent decides when to fetch the active webhook configurations via `list_payment_webhooks` and when to just read the cached invoice list.

Setup guide

Set up Getpaid 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 Getpaid 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({
    "getpaid-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 Getpaid 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 Getpaid. 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 Getpaid 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 Getpaid MCP in LangChain

Call `MultiServerMCPClient` with your Getpaid endpoint URL. Pass the resulting tool list into `create_agent` to start building billing pipelines.

Yes. Every call to `get_account_details` or `list_billing_payments` registers as a step in LangSmith. You see the exact execution time and input arguments.

You define the conditions in your prompt. The agent reads the tool schema and decides if the current context warrants issuing a return based on the transaction data.

Use `client.session()` to maintain state across multiple interactions. This keeps customer IDs in context so you don't repeat `list_billing_customers` calls.

The tools pull raw invoice arrays and checkout session IDs. LangChain processes this payload in memory during the chain execution, and you control whether LangSmith logs the raw strings or scrubs them before storage.

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