How to Use the Tingg Insights MCP in LangChain

Run multi-step payment workflows across African markets directly from your LangChain agent chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Tingg Insights MCP to LangChain

Create your Vinkius account to connect Tingg Insights to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Tingg Insights with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain live transaction checks and checkout requests

Look, here's the deal: this MCP Server connects your LangChain chains directly to active African payment pipelines. You don't want your agent guessing if the gateway is up—it starts by verifying your connection status using `check_api_health` before triggering any financial actions. Then, your agent can immediately generate a new payment link with `create_checkout_request` based on the user's LangChain chat input. We route this output directly into the next link in your run, meaning you don't have to glue things together manually. To keep your database updated, your agent monitors the payment lifecycle by calling `get_transaction_status` and pulls the recent history with `list_payment_transactions`. Expect full LangSmith tracing on every single raw API payload, making debugging painless.

Monitor performance and webhooks in LangChain

Get instant access to merchant performance metrics inside your agentic reasoning loops by connecting this MCP tool. The tool `get_account_performance_metrics` pulls live transaction volumes and success rates directly into your LangChain prompt context. By doing this, your agent analyzes regional payment trends without manual exports. Tracking operational health requires monitoring your external integrations. For full visibility, the system inspects your active push notifications using `list_configured_webhooks` and reconciles bank deposits with `list_account_settlements`. We pipe these raw inputs directly into your LangChain decision chains to flag settlement delays instantly.

Automate payouts and refunds with LangChain agents

Execute direct disbursements to mobile wallets by declaring payouts in your LangChain agent chains. Your agent invokes `initiate_payout_request` to send funds and then tracks the transfer to completion using `get_payout_status`. If a payment fails or requires reversal, the agent triggers `initiate_payment_refund` to return the funds. Managing these operations requires keeping both your team and your customers updated. To handle updates, the agent pulls a complete history of transfers using `list_disbursement_payouts` and fires off transactional alerts via `send_engagement_notification`. Your LangChain logs track every step for complete compliance auditing.

Setup guide

Set up Tingg Insights 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 Tingg Insights 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({
    "tingg-insights-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 Tingg Insights 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 Tingg Insights. 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 Tingg Insights 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 Tingg Insights MCP in LangChain

It exposes raw tools that you can plug directly into LangGraph or LangChain chains. Your agent calls them sequentially, passing the output of a checkout creation directly into a status check.

Yes, every tool invocation from this server is fully observable. You can monitor token usage, execution latency, and exact payload data for every African market transaction inside your LangSmith dashboard.

Vinkius manages the authentication layer so you do not need to store API keys in your LangChain environment. You simply connect using your single Vinkius endpoint token and the server handles the handshake.

Yes, your agents can run loops that check disbursement progress. The agent queries the API, waits, and branches based on the payment state.

All mobile wallet numbers, customer emails, and transaction amounts pass through a zero-trust, ephemeral MCP sandbox. Vinkius encrypts these inputs in transit and never stores your financial payloads on disk.

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