How to Use the AirOps MCP in LangChain

Q: How does LangChain handle long-running AirOps workflows?

Your agent triggers the job using executeworkflowasync and receives a unique execution ID. It then uses a loop to poll getexecutionstatus until the job finishes. This keeps your main application thread free to handle other tasks.

Chain AirOps workflows and memory searches directly inside LangChain using this fast MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirOps MCP to LangChain

Create your Vinkius account to connect AirOps 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 AirOps with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run synchronous AirOps workflows in LangChain

The `execute_workflow_sync` tool triggers immediate workflow runs and returns the output to your active chain. LangChain agents grab this raw data and feed it directly into the next step of your pipeline without manual parsing. This setup gives you instant execution for fast, linear tasks. You track the entire run through LangSmith to watch latency and token usage. If a step drags, you know exactly which node caused the bottleneck. You get complete visibility over your workflow executions.

Handle long-running AirOps tasks asynchronously

The `execute_workflow_async` tool starts background jobs so your agent doesn't sit idle during heavy processing. Your chain triggers the run, grabs the ID, and uses `get_execution_status` to check progress whenever it needs to. If a run goes sideways, the agent fires `cancel_execution` to kill the process instantly. This async pattern keeps your application responsive. Instead of blocking the thread, your model handles other user requests while AirOps processes the heavy lifting in the background. It keeps your compute costs low and your interface snappy.

Search and update memory stores with this MCP Server

The `search_memory_store` tool queries your AirOps vector database to find relevant context for your current prompt. Your agent pulls historical data, updates it with `add_memory_document`, and writes back fresh information to keep the knowledge base current. This loop ensures your system learns from every interaction. Connecting this MCP server to LangChain lets you combine vector search with over 500 external integrations. You build deep reasoning loops where the agent queries memory, processes the result through a database, and saves the updated context back to the store.

Setup guide

Set up AirOps 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 AirOps 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({
    "airops-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 AirOps 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 AirOps. 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 AirOps 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 AirOps MCP in LangChain

Install the required adapter package first using pip. Then, initialize the MultiServerMCPClient with your Vinkius HTTP endpoint and pass the tools directly into your agent constructor. This setup exposes all ten tools to your model in seconds.

Yes, every tool call automatically shows up in your LangSmith dashboard. You can inspect the exact inputs passed to `execute_workflow_sync` and see the raw outputs returned. This makes debugging complex multi-step chains straightforward.

Your agent triggers the job using `execute_workflow_async` and receives a unique execution ID. It then uses a loop to poll `get_execution_status` until the job finishes. This keeps your main application thread free to handle other tasks.

Absolutely. The multi-server client aggregates tools from different sources into a single list for your agent. You can mix database tools with these workflow tools in the same runtime.

Your data remains secure inside the Vinkius V8 isolate sandbox, which wipes all execution context the moment your session ends. AirOps memory documents and workflow payloads are transmitted over encrypted TLS connections directly to the secure endpoint. We never store or log your proprietary data on our intermediate 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