How to Use the NachoNacho MCP in LangChain

Q: How do I connect the NachoNacho MCP Server to LangChain?

Install langchain-mcp-adapters. Initialize a MultiServerMCPClient with your endpoint URL and pass the output of client.gettools() to your agent constructor.

Q: Does the agent maintain context across multiple queries?

The framework is stateless by default. You need to use client.session() to keep transaction history in context during a multi-step audit.

LangChain agents connect to this MCP Server to manage virtual cards and audit your SaaS spend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NachoNacho MCP to LangChain

Create your Vinkius account to connect NachoNacho 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 NachoNacho with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build SaaS Audit Chains

`list_transactions` and `list_subscriptions` feed raw payment data directly into your LangChain pipelines. You construct a ReAct agent that pulls a month of SaaS charges, isolates recurring billing, and flags anomalies. The output from the transaction list becomes the input for an LLM node that categorizes the spend. Tracing through LangSmith shows exactly how the agent navigated the API. If a specific subscription spikes, the chain automatically triggers `get_subscription` to isolate the vendor details before passing the context to a notification node.

Programmatic Virtual Card Controls

`create_card` and `update_card` let your agent spin up payment methods on demand. A developer requests a new tool in Slack. Your chain evaluates the request, provisions a single-use virtual card with a strict budget limit, and returns the credentials. You dictate the exact sequence of events. If a budget exceeds its threshold, the agent fires `freeze_card` instantly. No manual intervention happens here. The entire workflow executes as a deterministic chain of tool calls.

NachoNacho MCP Server Multi-Step Reasoning

`list_balances` and `list_cards` expose your total financial exposure across all active virtual cards. You bind these tools to a LangChain agent tasked with weekly reconciliation. The agent checks the aggregate balance, iterates through active cards, and compares limits against actual spend. Combining this with external database tools in the same chain lets you cross-reference payment data with internal employee directories. The agent identifies unused software seats and automatically suspends the associated accounts via `freeze_card`.

Setup guide

Set up NachoNacho 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 NachoNacho 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({
    "nachonacho-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 NachoNacho 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 NachoNacho. 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 NachoNacho 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 NachoNacho MCP in LangChain

Install `langchain-mcp-adapters`. Initialize a `MultiServerMCPClient` with your endpoint URL and pass the output of `client.get_tools()` to your agent constructor.

Yes. You configure a ReAct agent to monitor transaction limits and execute the freeze command when a threshold is breached.

LangSmith automatically logs every interaction. You see the exact payload sent to the API and the latency of the response.

The framework is stateless by default. You need to use `client.session()` to keep transaction history in context during a multi-step audit.

The MCP integration processes raw transaction amounts and vendor names. Vinkius runs the connection inside an ephemeral V8 Isolate Sandbox, destroying the memory state the second your script finishes 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