How to Use the Bold MCP in LangChain

Q: How do I track Bold transactions using LangChain and LangSmith?

Every tool call, including listtransactions and gettransaction, is automatically recorded when your agent is connected. You can inspect the exact card tokens, payment references, and COP amounts in your LangSmith dashboard.

Q: Can a LangChain agent generate a Bold payment link?

Yes, the agent can call createpaymentlink on demand. It generates a shareable URL with a specified COP amount and reference description, which the agent can then send to the customer.

Run multi-step Colombian payment workflows directly inside your LangChain graphs by connecting this MCP Server to Bold terminals and online checkouts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bold MCP to LangChain

Create your Vinkius account to connect Bold 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 Bold with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain terminal triggers with LangChain state

You can trigger physical card transactions directly from your LangChain graphs using `initiate_terminal_payment`. When your agent runs this tool, it can watch the transaction state and branch your execution path based on whether the customer taps their card in Bogotá or walks away. You can list active card reader hardware using `list_terminals` to ensure a physical device is online before pushing the COP amount. If a terminal drops offline, your chain catches the error and automatically routes the customer to `create_payment_link` instead.

Trace Colombian anti-fraud compliance in LangSmith

Your LangChain agents can process online transactions securely by calling `create_online_payment` with card tokenization and payer details. Having full visibility into these inputs prevents silent transaction failures during checkout since Colombian anti-fraud rules require precise payer information. If a payment fails, your agent can inspect the error payload, query `get_online_payment` to verify the failure code, and instantly notify your support team. This gives you a clear audit trail of every COP transaction without digging through raw server logs.

Build autonomous refund agents with this MCP Server

Automate your refund pipelines by letting LangChain agents trigger `refund_payment` based on customer conversation history. The agent uses `list_transactions` to locate the original charge and calls the refund tool to initiate the return back to the customer's card. Because refunds take 5 to 10 business days to clear, your chain can write the transaction details to your database and schedule a follow-up check. The agent uses `get_transaction` during subsequent runs to confirm the settlement status and keep the buyer informed.

Setup guide

Set up Bold 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 Bold 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({
    "bold-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 Bold 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 Bold. 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 Bold 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 Bold MCP in LangChain

Yes, you can initiate physical card transactions directly from your chains. Pass the serial number and COP amount to `initiate_terminal_payment` within a LangGraph node to control physical terminals in Colombia.

Every tool call, including `list_transactions` and `get_transaction`, is automatically recorded when your agent is connected. You can inspect the exact card tokens, payment references, and COP amounts in your LangSmith dashboard.

Yes, the agent can call `create_payment_link` on demand. It generates a shareable URL with a specified COP amount and reference description, which the agent can then send to the customer.

You do not need to manually configure webhooks in the merchant dashboard. Your LangChain code can programmatically register endpoints using `create_webhook` and clean them up with `delete_webhook` during runtime.

Yes, all sensitive payloads, including card tokenization details and payer anti-fraud data processed via `create_online_payment`, run through a secure V8 sandbox. Vinkius never stores your merchant credentials or transaction details, keeping your Colombian financial operations compliant and isolated.

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