How do I get a NASA API key?

Visit [**api.nasa.gov**](https://api.nasa.gov) and sign up with your email — it's completely free. You'll receive an API key instantly. For quick testing, you can use `DEMO_KEY` which allows 30 requests/hour and 50/day. Registered keys get 1,000 requests/hour.

Can I get Mars rover photos from today?

Mars rovers don't take photos every Earth day due to communication delays and mission schedules. Use `get_mars_photos` with rover name 'curiosity' or 'perseverance' and an earth_date parameter. If no photos exist for that date, the API returns an empty list. Try recent dates or browse available dates with `get_mars_rovers`.

What are Near-Earth Objects (NEOs)?

NEOs are asteroids and comets whose orbits bring them close to Earth. NASA tracks them for planetary defense. Use `get_neo_feed` to see asteroid counts and data over a date range. Each NEO includes estimated diameter, velocity, miss distance, and whether it's classified as 'potentially hazardous'.

Can I search NASA's image library?

Yes! Use `search_nasa_library` with a free-text query (e.g. 'Apollo 11', 'Mars', 'ISS', 'Hubble'). It searches thousands of images, videos and audio files. Results include title, description, NASA center, media type and URL. Optionally set page number for pagination.

NASA MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: NASA
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect NASA through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to NASA "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in NASA?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About NASA MCP Server

Connect to NASA's open APIs through any AI agent and explore space science through natural conversation.

Pydantic AI validates every NASA tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Astronomy Picture of the Day — Fetch today's APOD or any historical image with title, explanation and media URL
Mars Rover Photos — Browse photos from Curiosity, Perseverance, Opportunity and Spirit rovers by date and camera
Earth Satellite Imagery — View Landsat 8 satellite imagery for any coordinate on Earth with date filtering
EPIC Earth Images — See full-disk Earth images from the DSCOVR satellite's Deep Space Camera
Near-Earth Objects — Track asteroids and their size, velocity and hazard rating over a date range
NASA Library Search — Search NASA's extensive image and video library with free-text queries
Patent & Technology Transfer — Search NASA patents and discover technologies available for licensing

The NASA MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect NASA to Pydantic AI via MCP

Follow these steps to integrate the NASA MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from NASA with type-safe schemas

Why Use Pydantic AI with the NASA MCP Server

Pydantic AI provides unique advantages when paired with NASA through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your NASA integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your NASA connection logic from agent behavior for testable, maintainable code

NASA + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the NASA MCP Server delivers measurable value.

Type-safe data pipelines: query NASA with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple NASA tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query NASA and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock NASA responses and write comprehensive agent tests

NASA MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect NASA to Pydantic AI via MCP:

get_apod

If no date is specified, returns today's APOD. Optionally specify a single date, a date range (start_date and end_date), or a count of random APODs. Returns the image/video URL, title, explanation, copyright and date. This is one of NASA's most popular APIs. Get NASA Astronomy Picture of the Day (APOD)

get_earth_imagery

Requires longitude and latitude coordinates. Optionally specify a date (YYYY-MM-DD) to get imagery from a specific time. Returns the image URL and metadata. Useful for viewing geographic changes over time. Get satellite imagery of Earth from NASA

get_epic_images

Optionally specify a date (YYYY-MM-DD) and whether to use enhanced-color images (true) or natural-color (false, default). Returns image URLs, coordinates and acquisition time. Get Earth Polychromatic Imaging Camera (EPIC) images from NASA

get_mars_photos

Optionally filter by Earth date (YYYY-MM-DD), camera type (FHAZ, RHAZ, MAST, CHEMCAM, MAHLI, MARDI, NAVCAM, PANCAM, MINITES), and page number. Each photo includes the image URL, rover name, camera, Earth date and Mars sol date. Get Mars Rover photos from NASA

get_mars_rovers

Useful for discovering which rovers are active and when they last took photos. Get information about NASA Mars rovers

get_neo_feed

Optionally specify a start and end date (YYYY-MM-DD, max 7 days range). Returns asteroid count per day, estimated diameters, velocity, and whether they are potentially hazardous. Great for space awareness and planetary defense tracking. Get Near-Earth Object (NEO) feed from NASA

get_tech_transfer

Optionally filter by category (software, patent). Returns descriptions, contact information and availability status. Get NASA technology transfer information

search_nasa_library

Accepts a free-text query and returns matching media with titles, descriptions, NASA center information and media type (image, video, audio). Optionally set page number for pagination. This is the primary search endpoint for NASA media assets. Search the NASA Image and Video Library

search_patents

Requires a search query. Returns patent titles, numbers, abstracts and licensing availability. Useful for technology transfer and commercialization research. Search NASA patents

Example Prompts for NASA in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with NASA immediately.

"Show me today's Astronomy Picture of the Day."

"Show me photos taken by the Perseverance rover on Mars."

"Are there any potentially hazardous asteroids approaching Earth this week?"

Troubleshooting NASA MCP Server with Pydantic AI

Common issues when connecting NASA to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

NASA + Pydantic AI FAQ

Common questions about integrating NASA MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your NASA MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.