How to Use the Airship MCP in AutoGen

Q: How do I set up Airship with my AutoGen multi-agent system?

You use mcpservertools to load the definitions into your agents. The McpToolAdapter handles the communication so your agents can start calling functions immediately.

Let your AutoGen agents debate and execute Airship campaigns through consensus-driven tool calling.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airship MCP to AutoGen

Create your Vinkius account to connect Airship to AutoGen 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 Airship with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Airship campaigns in AutoGen

Deploy a security agent to check `get_push_status` while a marketing agent prepares `send_push_notification`. They discuss the risks and rewards before finalizing the delivery. This prevents accidental sends. The agents challenge each other's reasoning until they agree the conditions are perfect for the push.

Automate Airship tagging with AutoGen

Use `list_tags` and `list_segments` to feed your multi-agent team the context they need. Each agent reviews the audience state before proposing a new tagging strategy. They converge on a plan that matches your current audience growth. The process is transparent, and you see the entire conversation in your logs.

Resolve Airship device issues in AutoGen

Have one agent call `list_channels` while another uses `get_channel_details` to diagnose connectivity. They negotiate a solution to fix any identified device mapping errors. This team approach catches edge cases that a single agent might miss. It ensures your device records stay clean and accurate without your input.

Setup guide

Set up Airship MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Airship tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Airship_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Airship data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Airship_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Airship data")
    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 Airship. 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 Airship 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 Airship MCP in AutoGen

You use mcp_server_tools to load the definitions into your agents. The McpToolAdapter handles the communication so your agents can start calling functions immediately.

Yes, you pass the same tool list to every agent in your group chat. They will coordinate their calls to the MCP server based on their assigned roles.

You configure the group chat manager to handle the turn-taking logic. This ensures that only one agent executes a tool at a time, preventing race conditions.

The Vinkius endpoint manages your auth token. Your agents never see your secret keys, they only receive the tools needed to perform their tasks.

The server enforces a stateless connection, meaning we do not keep any logs of your push history. Every interaction is isolated in a secure, ephemeral process that resets after every task.

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