How to Use the Monnify MCP in LangChain

Q: How do I set up the Monnify MCP Server within my LangChain project?

Install the adapter package and initialize the MultiServerMCPClient with your Vinkius endpoint. Pass the tools retrieved from the server to your LangChain agent constructor to make them instantly available.

Q: How does LangChain trace failures in Monnify API calls?

LangSmith traces every single tool execution, including initpayment and gettransaction payloads. You can inspect the exact JSON input and output for every step to debug API errors or rate limits.

Q: What happens if a payment initialization fails inside a LangChain setup?

The initpayment tool returns the raw error code from the API. Your agent catches this exception in the chain and can automatically retry with adjusted parameters or log the error for manual review.

Run multi-step Nigerian payment verification and virtual account setups using LangChain and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Monnify MCP to LangChain

Create your Vinkius account to connect Monnify 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 Monnify with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain virtual account creation with LangChain

`reserve_account` initiates the creation of a dedicated virtual bank account for your Nigerian customers. Your LangChain agent handles this Monnify setup, feeds the output directly into your database chain, and links the generated account reference to a specific user profile without manual code. LangSmith records every step of this Monnify account generation process, showing you the exact payload sent to the API. If the customer needs to confirm their details, the LangChain agent runs `get_account_details` in the next link of the chain to verify the setup succeeded.

Automated payment reconciliation loops

`list_transactions` pulls the latest incoming Monnify payments directly into your active LangChain ReAct agent pipeline. The LangChain agent analyzes these Monnify transaction records, decides which ones require immediate processing, and triggers internal ledger updates based on real-time data. You don't have to write custom polling cron jobs for Monnify. Instead, LangChain chains these Monnify transaction checks with `list_settlements` via the MCP Server to verify that funds have cleared and are ready for disbursement.

Multi-step merchant payouts

`list_disbursements` inspects outgoing Monnify bank transfers to ensure payouts clear successfully. Your LangChain agent uses this tool inside a decision chain, matching outgoing Monnify records against bank codes fetched by `list_banks`. This LangChain setup prevents Monnify payment failures from stalling your operations. When a Monnify disbursement fails, the LangChain agent immediately flags the specific transaction ID and notifies your finance operations team through your existing alert chain.

Setup guide

Set up Monnify 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 Monnify 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({
    "monnify-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 Monnify 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 Monnify. 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 Monnify 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 Monnify MCP in LangChain

Install the adapter package and initialize the `MultiServerMCPClient` with your Vinkius endpoint. Pass the tools retrieved from the server to your LangChain agent constructor to make them instantly available.

Yes, your LangChain agent can process a list of users by looping the `reserve_account` tool. It handles each account reservation sequentially and pipes the resulting virtual account details to your database.

LangSmith traces every single tool execution, including `init_payment` and `get_transaction` payloads. You can inspect the exact JSON input and output for every step to debug API errors or rate limits.

The `init_payment` tool returns the raw error code from the API. Your agent catches this exception in the chain and can automatically retry with adjusted parameters or log the error for manual review.

All Monnify transaction data and reserved account numbers pass through Vinkius's secure V8 isolates. No financial data is stored on Vinkius servers, ensuring your customers' Nigerian bank details remain completely private.

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