How to Use the Kiwify MCP in LangChain

Q: How do I initialize the Kiwify MCP Server in my LangChain project?

Install the adapters first using pip. Then set up the MultiServerMCPClient pointing to the hosted URL. Pass the tools from client.gettools() to your agent creator to start executing commands.

Q: Can I build a multi-step refund verification chain with this setup?

You can write a chain that pulls recent transactions using listsaleshistory and runs conditional checks on specific items via getsaledetails to verify if a buyer qualifies for a course refund.

Build LangChain agents that trace subscription renewals and process real-time sales data from your Brazilian digital products.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kiwify MCP to LangChain

Create your Vinkius account to connect Kiwify 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 Kiwify with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate complex checkout tracking with LangChain chains

You want to track buyer behaviors across multiple stages without manual polling. Your agent uses `list_sales_history` to pull recent transactions, then feeds those IDs straight into `get_sale_details` in a single execution loop. LangChain manages this sequence by chaining the output of the first tool into the next. You can trace the entire execution path in LangSmith, showing you exactly when and why the agent fetched specific buyer records.

Dynamic webhook management inside agent workflows

Setting up instant notifications for digital course sales shouldn't require writing custom API wrapper scripts. Your agent calls the MCP server to trigger `create_notification_webhook` and register new endpoints instantly when a new product launch begins. If a campaign ends, the agent cleans up the endpoints using `delete_notification_webhook` and checks the state with `list_configured_webhooks`. This keeps your server environment clean without manual dashboard intervention.

ReAct-driven subscription monitoring and reporting

Recurring revenue requires constant vigilance, especially with high-churn digital products. The MCP integration allows the agent to use `list_active_subscriptions` to identify accounts that need attention. Because LangChain supports multi-server aggregation, you can combine this billing data with your SQL databases or CRM tools in one pass. The agent decides the execution order based on the live subscription status it reads.

Setup guide

Set up Kiwify 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 Kiwify 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({
    "kiwify-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 Kiwify 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 Kiwify. 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 Kiwify 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 Kiwify MCP in LangChain

Install the adapters first using pip. Then set up the `MultiServerMCPClient` pointing to the hosted URL. Pass the tools from `client.get_tools()` to your agent creator to start executing commands.

Yes. You configure separate client instances with unique tokens. The agent uses `get_account_summary` across each endpoint to compile unified reports for all your Brazilian digital storefronts.

The framework handles this through standard backoff strategies in your run loops. When calling `list_sales_history` or `get_product_details`, the agent pauses if the server signals a rate limit, preventing broken runs.

You can write a chain that pulls recent transactions using `list_sales_history` and runs conditional checks on specific items via `get_sale_details` to verify if a buyer qualifies for a course refund.

All customer emails, sales histories, and subscription statuses fetched via `get_sale_details` run in isolated V8 sandboxes. Vinkius provides an MCP gateway with single-token authentication so your credentials never leak to the LLM or external networks.

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