How to Use the Airship MCP in CrewAI

Q: How do I configure CrewAI agents to use the Airship MCP Server?

You can pass your Vinkius HTTP URL directly into the mcps array when defining your CrewAI agents. This exposes all push and channel tools to the entire crew.

Deploy specialized CrewAI agent teams to monitor, segment, and dispatch Airship mobile push campaigns.

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 CrewAI

Create your Vinkius account to connect Airship 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 Airship with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent push monitoring and dispatch via CrewAI

The `send_push_notification` tool allows your dispatch agent to send mobile alerts based on instructions from other team members. A researcher agent can analyze audience behavior, while a separate writer agent crafts the push copy. This cooperative structure uses shared memory to keep track of what was sent. The dispatch agent reads the finalized copy and triggers the notification, ensuring zero manual steps over the MCP connection.

Collaborative audience targeting using the CrewAI framework

The `list_segments` and `list_static_lists` tools provide the raw audience data your analyst agents need to evaluate campaign reach. One agent pulls the static lists, while a targeting specialist agent determines which segment matches the current promotion. The agents pass these segment details back and forth using sequential execution. Once the targeting agent approves the segment, the dispatch agent takes over to run the campaign over the MCP link.

Autonomous device and user mapping with CrewAI teams

The `associate_named_user` tool connects incoming user profiles to their physical devices under the supervision of a moderator agent. A monitoring agent tracks new sign-ups, while the moderator agent verifies the channel status using `get_channel_details` before linking them. This setup runs entirely in the background without human supervision. The crew coordinates the lookup, validation, and association steps, logging the entire process via the MCP Server in their shared memory.

Setup guide

Set up Airship 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 Airship tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Airship 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="Airship Analyst",
        goal="Access and analyze Airship data via MCP.",
        backstory="Expert analyst with direct Airship access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Airship 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 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 CrewAI

You can pass your Vinkius HTTP URL directly into the `mcps` array when defining your CrewAI agents. This exposes all push and channel tools to the entire crew.

Yes, you assign the copywriting task to one agent and the delivery task to another. The delivery agent uses the push tool to dispatch the finalized text produced by the writer.

You can restrict the send tool to a single moderator agent or set up strict tool filters. This keeps your creative agents focused on analysis while reserving execution for a single, controlled agent.

Yes, an analyst agent can call the segment details tool to read targeting rules. It can then share this information with the rest of the crew to refine the messaging strategy.

The MCP server runs inside a zero-trust V8 sandbox on Vinkius. Your CrewAI agents interact with the tools via secure HTTP, ensuring that your mobile push tokens and list details never touch external 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