How to Use the Airship MCP in Pydantic AI

Q: How do I load Airship into Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset using your Vinkius HTTP endpoint URL, then pass it in the toolsets array when defining your Agent.

Q: Can Pydantic AI read Airship audience data?

The agent can execute listnamedusers and listchannels. The framework parses the returned JSON into validated models, ensuring your downstream logic receives exactly the data types it expects.

Type-safe Airship integration for Pydantic AI agents.

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 Pydantic AI

Create your Vinkius account to connect Airship to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate messaging payloads

The Airship MCP Server connects your messaging infrastructure to strict runtime validation. When your agent decides to call `send_push_notification`, Pydantic AI checks the payload against your defined models before the request ever leaves the server. If the language model hallucinates a parameter, the framework throws a loud validation error instead of sending a broken push alert. You can then safely run `get_push_status` knowing the initial request was structurally sound.

Map users with strict typing

Managing identity through the MCP Server requires exact data structures. Your system relies on `associate_named_user` to link hardware to accounts, and the framework guarantees the resulting IDs match your internal schemas. The agent pulls `get_channel_details` to inspect device metadata. Any unexpected fields in the API response trigger an immediate halt, preventing corrupted device records from entering your database.

Read segments via Pydantic AI

Audience targeting rules are complex and prone to misinterpretation by LLMs. Your setup calls `list_segments` and `list_static_lists` to fetch available cohorts as strictly typed objects. The model then queries `get_segment_details` and `list_tags` to understand the criteria. Because Pydantic AI is model-agnostic, you get the exact same predictable output whether you run this logic through Claude, GPT-4, or a local open-source model.

Setup guide

Set up Airship MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "airship-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Airship tools.",
)

result = await agent.run("List recent Airship transactions")
print(result.output)

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 Pydantic AI

Install pydantic-ai-slim[mcp]. Create an MCPToolset using your Vinkius HTTP endpoint URL, then pass it in the toolsets array when defining your Agent.

Language models sometimes invent API parameters. Pydantic AI enforces strict schemas on tools like send_push_notification, catching bad inputs before they trigger live messages to your users.

The agent can execute list_named_users and list_channels. The framework parses the returned JSON into validated models, ensuring your downstream logic receives exactly the data types it expects.

Yes. You just pass the HTTP URL directly into MCPToolset. The older MCPServerHTTP class is deprecated, so the unified approach keeps your code clean and modern.

We run the MCP Server connection inside an ephemeral V8 Isolate. Push notification text, segment definitions, and named user IDs pass through memory only. Nothing gets written to disk.

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