How to Use the DoiT MCP in LangChain

Q: How does a LangChain agent search for resources using DoiT?

The agent runs searchcloudassets with a name keyword to find specific resources. It then uses getassetdetails to inspect that specific asset's configuration. This sequence runs automatically within your chain.

Q: What is the best way to monitor DoiT cost spikes in LangChain?

Use a ReAct agent configured with listcriticalcostspikes and getbillingcostsummary. The agent checks the high-severity spikes first. It then pulls the overall billing summary to put the spike in context.

Stop cloud spend spikes by letting your LangChain agents trace, analyze, and contain DoiT billing data in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DoiT MCP to LangChain

Create your Vinkius account to connect DoiT 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 DoiT with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track multi-cloud assets with LangChain chains

`list_cloud_assets` gives your LangChain agent direct visibility into every AWS, GCP, and Azure resource managed by your organization. No manual formatting is required because the agent handles the raw data. If the agent spots a weird resource, it immediately runs `get_asset_details` to inspect the exact configuration. You can trace this entire decision tree inside LangSmith using our MCP integration.

Stop budget overruns using sequential reasoning

`list_exceeded_cost_budgets` acts as the trigger for automated cost-containment chains in your LangGraph setup. First, the agent checks this budget data. Next, it decides whether to run secondary checks or alert your team. Combining this with `list_cost_budgets` maps out exactly where the leaks are happening. Structured JSON outputs allow your agent to pass the data directly to a notification step without breaking.

Automated anomaly detection via MCP Server tools

`list_critical_cost_spikes` isolates high-severity spending anomalies that need immediate human eyes. Running this tool on a cron job lets your LangChain agent filter out the noise. Only actual issues get flagged. Pairing this with `list_cost_anomalies` builds a timeline of unexpected spend. You get the raw facts, not guesses.

Setup guide

Set up DoiT 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 DoiT 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({
    "doit-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 DoiT 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 DoiT. 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 DoiT 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 DoiT MCP in LangChain

Install the adapter package using pip install langchain-mcp-adapters langgraph. Initialize the MultiServerMCPClient with your Vinkius endpoint. Retrieve the tools using client.get_tools() and pass them directly to your agent constructor.

The agent runs search_cloud_assets with a name keyword to find specific resources. It then uses get_asset_details to inspect that specific asset's configuration. This sequence runs automatically within your chain.

Use a ReAct agent configured with list_critical_cost_spikes and get_billing_cost_summary. The agent checks the high-severity spikes first. It then pulls the overall billing summary to put the spike in context.

Yes. The MultiServerMCPClient aggregates tools from this server alongside your other active servers. Your agent sees them all as a unified toolset.

Your credentials never touch Vinkius. The MCP Server runs inside a secure, ephemeral sandbox. It only reads metadata like organization billing summaries and asset configurations to analyze costs, leaving your actual infrastructure untouched.

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