How to Use the Bolt MCP in LangChain

Chain together Bolt payments and order workflows directly inside your LangChain agents for precise financial logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bolt MCP to LangChain

Create your Vinkius account to connect Bolt 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 Bolt with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate order tokens in LangChain

Generate checkout tokens on the fly by invoking `create_order_token` within your agentic chains. You skip the manual web dashboard and let the agent handle the handshake between your frontend and payment gateway. This keeps your transaction flow strictly within your Python logic. The agent captures the token output and immediately passes it to the next step in your sequence.

Chain transaction status checks

Feed the output of `list_transactions` directly into your reasoning loop. Your agent checks the recent history to decide if a specific order needs a follow-up action based on current status. Because every tool call is a link, your chain stays observable. You see exactly how the agent moved from listing records to identifying a payment that needs attention.

Manage refunds via MCP Server logic

Trigger `refund_transaction` based on agent analysis of your order database. If your chain detects a return request, it executes the refund without you writing custom boilerplate code. This MCP Server provides the granular control needed for automated customer support. The agent confirms the outcome of the refund before closing the ticket chain.

Setup guide

Set up Bolt 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 Bolt 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({
    "bolt-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 Bolt 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 Bolt. 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 Bolt 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 Bolt MCP in LangChain

Install the MCP adapters and point your client to the Vinkius endpoint URL. You then inject the tools into your agent definition so the model can access the payment methods.

Yes, use the client session feature to keep context across multiple chain turns. This ensures the agent remembers your merchant details during long-running reasoning tasks.

Absolutely, the agent manages the sequence by calling the tools in order. It creates the token, verifies the status, and then finalizes the transaction based on your custom logic.

Vinkius handles the underlying transport security for your connection. Your agent only sees the data returned by the tools it is authorized to call.

Your financial records never leave the encrypted pipe between the server and the agent. The system only processes order IDs and status strings necessary to complete your requested financial operations.

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