How to Use the Mollie MCP in LangChain

Run multi-step payment reconciliation chains in LangChain using Mollie to track, refund, and verify transactions automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mollie MCP to LangChain

Create your Vinkius account to connect Mollie 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 Mollie with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Mollie payment lookups in LangChain

Your LangChain agents check transactions using `list_payments` and trigger refunds back-to-back. The output feeds directly into `list_refunds` in your LangChain pipeline to audit disputed charges without manual script writing. LangSmith traces every step of the Mollie tool run, showing you exact token costs and execution latency for each API call. This setup replaces brittle custom glue code with clean, observable LangChain links for your Mollie integration. You pass the Mollie server tools directly to your LangChain agent initialization, allowing the model to decide when to trigger `get_payment_details` based on customer chat history.

Automate subscription audits via active chains

LangChain chains audit your customer base using `list_customers` and then fetch active cycles via `list_customer_subscriptions`. Instead of writing complex cron jobs to audit billing anomalies, let your LangChain agent handle Mollie billing directly. Because the Vinkius MCP Server handles Mollie authorization transparently, your LangChain agent doesn't need raw API keys. The LangChain model simply calls the Mollie endpoints it needs to build a complete customer billing profile.

Dynamic local checkout routing

Configure your LangChain routing chains to query active Mollie checkout options using `list_payment_methods` before presenting payment links. By running this tool, the LangChain agent dynamically adjusts options based on the user's country code to prevent checkout abandonment. Once the LangChain agent selects the optimal method, it calls `create_payment` to generate the Mollie checkout URL. This keeps your European checkout flow optimized in LangChain without hardcoding regional payment rules.

Setup guide

Set up Mollie 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 Mollie 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({
    "mollie-alternative-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 Mollie 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 Mollie. 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 Mollie 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 Mollie MCP in LangChain

Install the LangChain MCP adapter and connect the MCP Server via Vinkius. Call `get_tools()` and pass the array directly to your LangChain agent constructor to expose Mollie commands like `create_payment`.

Yes. Combine the Mollie tools with any database retriever in the same LangChain agent. The LangChain agent can search your internal docs for refund policies and then execute Mollie's `list_refunds` to resolve a customer issue.

LangSmith tracks the inputs and outputs of Mollie tools like `get_payment_details` inside your LangChain pipelines in real time. You get full visibility into the exact JSON payloads sent to the Mollie API and the time each LangChain call took.

Yes, you can aggregate this Mollie server with other MCP tools in a single LangChain client. The LangChain adapter manages the tool schemas so your agent can query Mollie billing data alongside CRM details.

Your customer emails and transaction amounts processed by LangChain never persist on Vinkius. The server runs in an ephemeral, zero-trust V8 isolate that processes Mollie payload data in memory and discards it immediately after the API call completes.

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