How to Use the Wise MCP in LangChain

Q: How do I track historical transfers using Wise and LangChain?

You call listtransfers on the MCP Server. This function pulls all recorded transfer details into a list, letting your agent process history directly within the chain's memory.

Q: Can I manage multiple currencies using Wise and LangChain?

Yes. Use listbalances to see balances across various currencies simultaneously. Your agent can then use this multi-currency data to accurately determine available funds before creating a quote.

Q: Can I find payment recipients using Wise and LangChain?

You use the listrecipients tool. This lets your agent pull a list of known payees, making it easy to verify who needs funds before running any transfer commands.

Q: Does Wise and LangChain support quote generation?

Absolutely. The createquote function allows the agent to generate an immediate transfer quote based on current rates and selected currencies, all within a single chain execution.

Build multi-step finance agents with LangChain using Wise 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 Wise MCP to LangChain

Create your Vinkius account to connect Wise 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 Wise with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Multi-Step Finance Logic via LangChain

Your AI agent decides the path through complex financial operations. You can chain a call like `list_balances` to get current funds, and then immediately pass that data to `create_quote` to model a transfer. The output of one tool becomes the necessary input for the next step in your reasoning pipeline. This sequence allows agents to handle real-world financial decisions. For instance, an agent can first use `list_profiles` to check which business accounts are available before running `get_balance` on a specific profile.

Managing Transfers and History with MCP Server

Track every penny without ever opening the Wise web interface. Use `list_transfers` to pull an entire history of transactions, then use `get_transfer` to drill down into a specific payment's status. This provides a complete audit trail that agents can process. Need proof of funds? The agent uses `list_statements` to fetch account statements directly via the MCP Server. It also lets you check all possible recipients by calling `list_recipients`, keeping your entire system self-contained.

Real-Time Currency and Quote Generation for LangChain

When an agent needs to model a payment, it doesn't need guesswork. It first calls `get_currencies` to confirm supported types, then uses `get_exchange_rate` for live data. Finally, the agent executes `create_quote`, delivering a precise, actionable quote that can be used by other parts of your chain. This mechanism is critical for accurate financial planning within complex chains. It keeps the entire process—from currency check to final transfer modeling—within the control flow of your application.

Setup guide

Set up Wise 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 Wise 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({
    "wise-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 Wise 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 Wise. 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 Wise 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 Wise MCP in LangChain

You call `list_transfers` on the MCP Server. This function pulls all recorded transfer details into a list, letting your agent process history directly within the chain's memory.

Yes. Use `list_balances` to see balances across various currencies simultaneously. Your agent can then use this multi-currency data to accurately determine available funds before creating a quote.

The server touches account statement data, which is typically sensitive financial records. Always ensure your agent's access permissions are scoped down to only what's necessary for its task.

You use the `list_recipients` tool. This lets your agent pull a list of known payees, making it easy to verify who needs funds before running any transfer commands.

Absolutely. The `create_quote` function allows the agent to generate an immediate transfer quote based on current rates and selected currencies, all within a single chain execution.

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