How to Use the NASA APOD — Astronomy Picture of the Day MCP in Pydantic AI

Q: How does the NASA APOD — Astronomy Picture of the Day server work with Pydantic AI validation?

When your agent calls a tool like getapod, Pydantic AI intercepts the JSON response from the MCP server and validates it against an inferred Pydantic model. If it doesn't match, it errors out.

Q: What's the setup process for the NASA APOD — Astronomy Picture of the Day server and Pydantic AI?

After installing pydantic-ai-slimmcp, you create an MCPToolset instance with your Vinkius URL. Then you pass it into your Agent's toolsets list.

Q: What happens if the NASA APOD API changes unexpectedly?

Your Pydantic AI agent will immediately raise a ValidationError the next time it calls a tool. This is a huge benefit, as it alerts you to the breaking change instead of failing silently.

Pull NASA's Astronomy Picture of the Day with Pydantic AI. Get type-safe, validated results from the 30-year archive, or get a clear error. No surprises.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA APOD — Astronomy Picture of the Day MCP to Pydantic AI

Create your Vinkius account to connect NASA APOD — Astronomy Picture of the Day 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 NASA APOD — Astronomy Picture of the Day with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Data, Or Nothing

The `get_apod` tool fetches NASA's daily picture, but with a Pydantic AI agent, it does more. The JSON response is automatically parsed and validated against a Pydantic model before it ever reaches your code. If the API ever returns a malformed response or an unexpected data type, your agent will raise a `ValidationError`. This means no silent data corruption and no time wasted debugging weird API outputs.

Explore the Archive with Confidence

Use the `get_apod_range` and `get_random_apod` tools to pull multiple images from the archive. Pydantic AI validates each item in the returned list. This is critical when you're processing data in a loop. You can be sure that every single record conforms to your expected schema, preventing runtime errors deep inside your application logic. Your agent gets clean, predictable objects every time.

A Model-Agnostic MCP Server

This MCP Server provides the tools; Pydantic AI provides the brain-agnostic plumbing. You can connect this server to an agent powered by OpenAI, Gemini, Anthropic, or even a local model. The `MCPToolset` handles the interaction, ensuring that no matter which LLM is driving the agent, the tool calls and responses are structured and validated correctly. It separates the logic of 'what to do' from 'how to do it.'

Setup guide

Set up NASA APOD — Astronomy Picture of the Day 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": {
        "nasa-apod-astronomy-picture-of-the-day-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NASA APOD — Astronomy Picture of the Day tools.",
)

result = await agent.run("List recent NASA APOD — Astronomy Picture of the Day 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 NASA. 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 NASA APOD — Astronomy Picture of the Day 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 NASA APOD — Astronomy Picture of the Day MCP in Pydantic AI

When your agent calls a tool like `get_apod`, Pydantic AI intercepts the JSON response from the MCP server and validates it against an inferred Pydantic model. If it doesn't match, it errors out.

After installing `pydantic-ai-slim[mcp]`, you create an `MCPToolset` instance with your Vinkius URL. Then you pass it into your `Agent`'s `toolsets` list.

Yes. Pydantic AI is model-agnostic. You can use the same MCP toolset with agents running on OpenAI, Anthropic, or other models, and the tool-use logic remains consistent.

Your Pydantic AI agent will immediately raise a `ValidationError` the next time it calls a tool. This is a huge benefit, as it alerts you to the breaking change instead of failing silently.

The server only ever requests public data from the NASA APOD API, like image URLs, dates, and the text of the explanations. With Pydantic AI, the runtime validation acts as a security check, ensuring the data returned from the API conforms exactly to the expected structure, preventing unexpected data from entering your system.

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