How to Use the AirOps MCP in CrewAI

Q: How can one CrewAI agent start an AirOps job and another check its status?

The first agent calls executeworkflowasync and shares the returned execution ID through CrewAI's shared memory. The second agent can then pick up that ID and use getexecutionstatus to monitor the job's progress.

Assemble autonomous agent crews that orchestrate AirOps. Give your CrewAI teams the tools to execute, monitor, and manage complex AI workflows.

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 CrewAI

Create your Vinkius account to connect AirOps to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate Workflow Execution to a Specialist Agent

This is what CrewAI was built for. Assign one agent the `execute_workflow_async` and `execute_workflow_sync` tools. This agent's entire job is to kick off tasks in AirOps based on instructions from the rest of the crew. A monitor agent can then use `get_execution_status` and `cancel_execution`. If a workflow hangs or fails, the monitor reports back to the crew manager to decide the next step.

Create a Research & Analysis Crew

Equip a 'Researcher' agent with the `upload_file` and `add_memory_document` tools. Its job is to find and index new information into the AirOps memory store. It constantly feeds the knowledge base. Then, an 'Analyst' agent uses `search_memory_store` to query that knowledge. It pulls relevant context and passes it to an 'Action' agent to perform a final task. This divides the labor, making the whole operation more efficient.

Build a Self-Managing CrewAI System

This MCP Server lets your crew manage the tools themselves. An 'Operations' agent can use `list_apps` to see all available AirOps applications. It can then use `get_app_details` to understand what each app does. Based on this info, the crew can dynamically re-assign tasks or even decide to use a different AirOps app for a job. This is how you move from simple task execution to truly autonomous operations.

Setup guide

Set up AirOps MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke AirOps tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="AirOps Analyst",
    goal="Access and analyze AirOps data via MCP.",
    backstory="Expert analyst with direct AirOps access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent AirOps transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="AirOps Analyst",
        goal="Access and analyze AirOps data via MCP.",
        backstory="Expert analyst with direct AirOps access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AirOps transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

The first agent calls `execute_workflow_async` and shares the returned execution ID through CrewAI's shared memory. The second agent can then pick up that ID and use `get_execution_status` to monitor the job's progress.

For a quick start, pass your Vinkius MCP endpoint URL into the `mcps` list when defining your Agent. If you need more control, use `MCPServerHTTP` and the `tool_filter` to assign specific tools to specific agents.

Yes, that's a perfect use case. You can have one agent dedicated to adding information with `add_memory_document` and another that's an expert at finding it with `search_memory_store`.

It allows an agent in your crew to have a conversation with an external agent hosted in AirOps. Think of it as your crew hiring an outside specialist for a very specific task that none of the crew members can do.

The server processes the data your agents send, which includes workflow definitions, document text via `add_memory_document`, and any files sent with `upload_file`. Vinkius ensures each connection is isolated in its own V8 sandbox, and the compute environment is ephemeral, meaning it's torn down after use.

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