How to Use the Belvo MCP in LangChain

Q: Can LangChain agents handle Belvo transaction pagination?

Yes. ReAct agents automatically loop through listtransactions when they hit pagination limits. You just need to instruct the agent to check for next-page tokens.

Connect Latin American banking data via the Belvo MCP Server directly into your LangChain agents for automated financial workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Belvo MCP to LangChain

Create your Vinkius account to connect Belvo 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 Belvo with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain LatAm banking data in LangChain

Calling `list_institutions` lets your agent identify supported banks before attempting connection. You pipe that output straight into a routing chain that selects the right regional processing logic. Financial workflows need strict sequence control. ReAct agents can pull specific connection details via `get_link` and then immediately fetch `get_account` data based on that link ID. The MCP Server tracks the exact latency of these API calls across the Vinkius infrastructure.

Analyze recurring expenses automatically

Running `list_recurring_expenses` feeds structured subscription data directly into your prompt templates. Agents parse this output to calculate monthly burn rates without human intervention. Raw transaction histories get messy quickly. Pumping `list_transactions` through a LangChain map-reduce pipeline categorizes thousands of bank records in seconds. You get clean, structured JSON back.

Build multi-step investment pipelines

Fetching portfolio data with `get_investments` provides the baseline for automated wealth analysis. Your agent takes those holdings and queries external market APIs in the very next chain step. Context windows fill up fast when dealing with heavy financial records. Using `list_balances` alongside `list_incomes` gives the LLM a lightweight summary of a user's cash flow before diving into deeper transaction queries.

Setup guide

Set up Belvo 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 Belvo 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({
    "belvo-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 Belvo 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 Belvo. 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 Belvo 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 Belvo MCP in LangChain

Install the langchain-mcp-adapters package. Pass your Vinkius endpoint URL into MultiServerMCPClient and call get_tools() to initialize the connection.

Yes. ReAct agents automatically loop through list_transactions when they hit pagination limits. You just need to instruct the agent to check for next-page tokens.

LangChain handles the reasoning loop. Instead of writing custom logic to fetch a link and then its accounts, the agent decides to call get_link and list_accounts sequentially based on the user's prompt.

Every tool execution logs directly to LangSmith. You see exactly how many tokens were spent parsing list_incomes or list_owners payloads.

Vinkius runs the Belvo integration inside an ephemeral V8 Isolate Sandbox. Account numbers and transaction histories pass directly to your environment without resting on our servers.

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