How to Use the NASA DONKI — Space Weather Intelligence MCP in Pydantic AI

Q: How do I connect Pydantic AI to NASA DONKI — Space Weather Intelligence?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your HTTP endpoint. Pass that toolset to your Agent instance. Remember that the older MCPServerHTTP method is deprecated.

Q: Can the agent track multiple solar threats simultaneously?

Yes. Your agent calls getcme and getgeomagneticstorms in parallel. Pydantic validates both responses independently before the LLM synthesizes a final threat assessment.

Build type-safe space weather agents with Pydantic AI to validate every NASA DONKI telemetry response.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA DONKI — Space Weather Intelligence MCP to Pydantic AI

Create your Vinkius account to connect NASA DONKI — Space Weather Intelligence 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 DONKI — Space Weather Intelligence with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict schemas on MCP Server data

The `get_geomagnetic_storms` and `get_cme` tools return complex nested JSON detailing Kp indices and magnetic field vectors. Pydantic AI validates every single field against your defined models before your agent even sees it. If NASA changes a field name or an API timeout drops a parameter, your application fails loudly. You get a clear validation error instead of a hallucinated Kp=2 reading that tricks your automated systems into a false sense of security.

Parse extreme solar events with zero hallucinations

The `get_solar_flares` tool pulls exact begin, peak, and end times for solar events. You need this data to be perfectly accurate, because X-class flares dictate immediate communication protocol shifts. Your type-safe agent cross-checks these flare timings with `get_donki_notifications`. Since Pydantic AI is model-agnostic, you swap between Anthropic and local models to analyze the threat without rewriting your validation logic.

Track interplanetary shocks reliably

The `get_interplanetary_shocks` and `get_solar_energetic_particles` tools provide the raw physics data required to protect astronauts and satellites. These shocks precede massive geomagnetic disruptions. You build a monitoring pipeline that demands strict float values for shock speeds and particle densities. The agent queries the tools, Pydantic casts the types, and your orbital hardware adjusts its shielding parameters based on proven facts.

Setup guide

Set up NASA DONKI — Space Weather Intelligence 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-donki-space-weather-intelligence-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NASA DONKI — Space Weather Intelligence tools.",
)

result = await agent.run("List recent NASA DONKI — Space Weather Intelligence 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 DONKI — Space Weather Intelligence 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 DONKI — Space Weather Intelligence MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your HTTP endpoint. Pass that toolset to your Agent instance. Remember that the older `MCPServerHTTP` method is deprecated.

Runtime validation. Space weather data dictates expensive operational decisions. Pydantic AI guarantees your agent receives exact schema matches for `get_radiation_belt` data, preventing silent failures.

Yes. Your agent calls `get_cme` and `get_geomagnetic_storms` in parallel. Pydantic validates both responses independently before the LLM synthesizes a final threat assessment.

The Pydantic AI framework intercepts the response and throws a validation error. The agent never processes the corrupted `get_solar_flares` payload, keeping your downstream systems safe.

By isolating the external query boundary. The server only retrieves public variables like coronal mass ejection speeds. Your internal Pydantic models act as a strict firewall, ensuring no unexpected payload shapes enter your execution environment.

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