How to Use the Modulr MCP in LangChain

Q: How do I configure the Modulr MCP server within a LangChain agent?

Install the required packages using pip install langchain-mcp-adapters langgraph. Then, initialize the MultiServerMCPClient with the Vinkius endpoint URL and pass the tools retrieved via client.gettools() directly into your agent constructor.

Q: Can my LangChain pipeline manage multiple currencies with Modulr?

Yes. Your agent can use modulrcreateaccount to open either GBP or EUR accounts dynamically. The agent decides the correct currency parameter based on the incoming payload before executing the tool.

Q: How does LangChain handle failed Modulr payments?

You can build a self-correcting LangGraph loop. When modulrcreatepayment returns an error, the agent uses modulrlistpayments to verify the state of the payment array before deciding to re-run the transfer.

Build LangChain agents that spin up European ledgers and trigger high-volume payouts with strict HMAC security.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modulr MCP to LangChain

Create your Vinkius account to connect Modulr 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 Modulr with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Ledger Setup in LangChain

The `modulr_create_account` tool lets your agent provision dedicated UK and EU accounts on demand. Instead of manually configuring IBANs or waiting on slow banking interfaces, your LangChain pipeline handles account creation programmatically as a step in your onboarding flow. This means you can chain account provisioning directly into your user registration logic. By combining this tool with LangChain's memory modules, your agent remembers the newly created account details to execute subsequent routing steps without manual intervention.

Chain-Linked Payment Execution

The `modulr_create_payment` tool triggers outgoing Faster Payments or SEPA transfers directly from your active chains. Your agent evaluates business logic, verifies routing data, and executes the payout in a single, unblocked execution loop. You can trace every single payment step using LangSmith to monitor latency and token usage through the MCP server interface. If a payout fails, the agent inspects the error and uses `modulr_list_payments` to check the status of the batch before attempting a safe retry.

Audit Accounts via LangChain MCP Server

The `modulr_get_transactions` tool pulls complete transaction histories for any active ledger to verify settlement. Your chain can inspect raw ledger data immediately after triggering a payout to verify that the funds actually cleared. This setup removes the need for manual CSV exports or separate database syncs. Our integration reads directly from the Modulr API, comparing live transaction records against your internal database to flag discrepancies on the fly.

Setup guide

Set up Modulr 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 Modulr 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({
    "modulr-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 Modulr 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 Modulr Finance. 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 Modulr 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 Modulr MCP in LangChain

Install the required packages using `pip install langchain-mcp-adapters langgraph`. Then, initialize the `MultiServerMCPClient` with the Vinkius endpoint URL and pass the tools retrieved via `client.get_tools()` directly into your agent constructor.

Yes. Your agent can use `modulr_create_account` to open either GBP or EUR accounts dynamically. The agent decides the correct currency parameter based on the incoming payload before executing the tool.

You can build a self-correcting LangGraph loop. When `modulr_create_payment` returns an error, the agent uses `modulr_list_payments` to verify the state of the payment array before deciding to re-run the transfer.

No. The Vinkius managed MCP server handles the complex HMAC-SHA256 signature generation and header construction automatically. Your agent simply passes standard JSON payloads, and the server secures the transport layer.

All transaction records, customer details, and IBANs are processed within an isolated V8 sandbox environment on the Vinkius MCP platform. Vinkius uses ephemeral execution blocks that destroy session data immediately after your agent completes the tool call.

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