How to Use the Recharge MCP in LangChain

Q: Can a LangChain agent cancel a Recharge subscription?

Yes, the agent can invoke cancelsubscription if you grant it write permissions. To protect your monthly recurring revenue, you should configure your chain to require human approval before this specific tool executes.

Run multi-step Recharge subscription workflows directly inside your LangChain reasoning loops with full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Recharge MCP to LangChain

Create your Vinkius account to connect Recharge 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 Recharge with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain subscription updates in LangChain

The `update_subscription` tool lets your agent modify active orders, while `list_shipping_addresses` checks where the items are headed. Your agent can run these sequentially, passing the verified address from one step directly into the subscription modification. LangChain coordinates this sequence as a single execution block. If a step fails, you see exactly where the chain broke inside LangSmith, showing you the raw payload sent to the Recharge API.

Trace subscriber lookups with LangSmith

The `get_customer` tool pulls specific subscriber profiles, and `list_subscription_orders` extracts their entire transactional history. By connecting these tools to your ReAct agent, you let the model decide when to pull history before making billing changes. This setup avoids hardcoded logic. Your agent executes tool calls based on live customer inquiries, logging every API call and token count directly to your central LangSmith dashboard.

Validate billing charges via MCP Server tools

The `list_billing_charges` tool retrieves transaction histories, which your agent can cross-reference with active subscriptions using `list_subscriptions`. This MCP Server connection lets your LangChain pipeline run automated audits of payment records without manual exports. You can combine this with local databases in your chain. The agent pulls the Recharge data, compares it against your SQL records, and flags discrepancies in a single run.

Setup guide

Set up Recharge 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 Recharge 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({
    "recharge-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 Recharge 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 Recharge. 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 Recharge 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 Recharge MCP in LangChain

You should implement a retry mechanism inside your LangChain tool-calling agent. The Recharge API limits requests to 40 per minute, so setting up an exponential backoff wrapper around the MCP Server tools prevents execution failures during high-volume runs.

Yes, you can register the MCP Server tools within a LangGraph state machine. This lets you build complex, multi-agent customer retention loops where one agent checks active plans via `list_subscriptions` and another handles the `cancel_subscription` logic based on user sentiment.

Your LangChain agent extracts the customer ID from the user's prompt and passes it directly to `get_customer`. The MCP client handles the JSON schema validation, ensuring the ID formats correctly before hitting the Recharge endpoints.

Yes, the agent can invoke `cancel_subscription` if you grant it write permissions. To protect your monthly recurring revenue, you should configure your chain to require human approval before this specific tool executes.

All customer billing charges and profile data stay within your local network or V8 sandbox environment. Vinkius secures your Recharge API tokens, meaning your LangChain client never exposes keys to the LLM or any external logging service.

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