How to Use the MoonClerk MCP in LangChain

Q: Can LangChain agents run multiple MoonClerk tools in a single chain?

Yes, your LangChain agent can call listcustomers to find an ID and then immediately pass that ID to listsubscriptions in a single execution loop.

Fetch MoonClerk payment data directly inside your LangChain reasoning loops using this secure MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MoonClerk MCP to LangChain

Create your Vinkius account to connect MoonClerk 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 MoonClerk with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain MoonClerk data with LangChain agents

The `list_subscriptions` tool pulls live subscriber status directly into your LangChain runnable sequences. Your agent uses this data to decide the next step in a multi-step billing support chain, feeding the output of one step into another. No manual glue code is required to pass payload data between steps. LangSmith tracks the entire execution of these chained tools in real time. You see the exact latency and token usage of your `list_subscriptions` calls, making it easy to debug slow payment checks.

Track payments inside reasoning loops

The `list_payments` tool lets your agent inspect transaction records dynamically during customer support chat sessions. When a user asks about a missing charge, the agent calls this tool to retrieve recent transaction history before generating its response. This runtime tool execution feeds directly into your LangChain agent's memory. Instead of hardcoding API requests, you let the agent decide when it needs to inspect past payments based on the conversation flow.

Verify subscription plans dynamically via MCP Server

The `get_plan` tool retrieves specific pricing tiers to verify access levels inside your LangChain application. Your agent queries the active plan details to confirm what features a customer should have access to based on their active billing status. This keeps your application logic simple since you do not have to write custom database sync scripts. The agent queries MoonClerk directly, cross-referencing the results with your vector store or database integrations in the same chain.

Setup guide

Set up MoonClerk 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 MoonClerk 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({
    "moonclerk-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 MoonClerk 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 MoonClerk. 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 MoonClerk 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 MoonClerk MCP in LangChain

Install the adapter using pip, then pass the Vinkius server URL to your MultiServerMCPClient. Call get_tools to register the MoonClerk endpoints so your LangChain agent can call them.

Yes, your LangChain agent can call `list_customers` to find an ID and then immediately pass that ID to `list_subscriptions` in a single execution loop.

Use LangSmith to monitor every tool invocation. It captures the inputs and outputs of tools like `get_payment` so you can debug latency issues.

Yes, you can mix these payment tools with any database or vector store tool inside the same LangChain agent executor.

Vinkius runs the server in an isolated sandbox. Your raw customer details, payments, and subscriptions are only accessed in memory during active tool execution and are never saved on our servers.

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