How to Use the Recurly MCP in LangChain

Q: Can my LangChain agent apply discounts via Recurly?

Your agent uses listcoupons to find active promotions and apply them. You can write a chain that matches customer profiles with available discounts before updating their account details. This avoids hardcoding promotion logic into your application.

Run complex billing workflows by chaining Recurly tools directly into your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Recurly MCP to LangChain

Create your Vinkius account to connect Recurly 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 Recurly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step billing chains with this MCP Server

The Recurly MCP Server exposes eleven live billing tools directly to your LangChain graph. You can feed the output of `list_subscriptions` straight into `get_invoice` without manual glue code. This lets your agent inspect unpaid balances and immediately locate the exact invoice causing the block. LangSmith traces every single hop of this process. You see the raw inputs, the exact tool execution latency, and the final outputs in your dashboard. It makes debugging complex subscription logic incredibly straightforward because you aren't guessing what the agent did.

Automate account setup within LangChain workflows

This MCP Server provides the `create_billing_account` tool to register new customers during conversational onboarding. Your agent captures user details, validates them, and registers the account in one shot. If the user has a discount code, the agent calls `list_coupons` to confirm it first. You get a deterministic flow built on top of raw LLM reasoning. Combining these tools with your existing vector stores or databases in the same chain creates a unified user provisioning pipeline. The agent decides when to pull the trigger based on user inputs.

Trace revenue exports using LangChain tools

The Recurly integration lets your agent run financial checks using `get_revenue_summary` and `list_transactions`. Instead of writing custom cron jobs, you let your ReAct agent fetch the latest transaction history. It handles the pagination and formats the numbers for your reporting chains. Every tool call behaves like a native LangChain runnable. This means you can swap LLMs, add fallback models, or inject custom prompts without rewriting your billing integration. You write the logic once, and the adapter handles the rest.

Setup guide

Set up Recurly 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 Recurly 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({
    "recurly-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 Recurly 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 Recurly. 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 Recurly 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 Recurly MCP in LangChain

Yes, every tool execution shows up in LangSmith automatically. You get full visibility into latency, token counts, and the exact payloads passed to tools like `get_subscription_details`. This makes debugging agent decisions simple.

You pass multiple endpoints to the MultiServerMCPClient during initialization. The client aggregates the tools, allowing your agent to query Recurly data and database records in a single turn. It routes the requests to the correct server based on the tool schema.

Your agent uses `list_coupons` to find active promotions and apply them. You can write a chain that matches customer profiles with available discounts before updating their account details. This avoids hardcoding promotion logic into your application.

Install the adapter package and initialize the client with your Vinkius endpoint. You then fetch the tools and pass them directly to your agent constructor. The entire process takes fewer than ten lines of Python.

Vinkius runs this server inside an isolated, zero-trust V8 sandbox. Your API keys, transaction histories, and invoice records never persist on the host system. Every session is ephemeral and completely separated from other workloads.

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