How to Use the NASA MCP in Pydantic AI

Q: Can I query Mars rover photos by specific cameras?

Yes, the getmarsphotos tool accepts camera parameters like MAST, MAHLI, or PANCAM. The tool returns structured schemas containing the photo URL, rover details, and Martian sol date.

Q: How are my coordinates and patent queries protected?

Coordinate inputs for getearthimagery and search queries for searchpatents are processed directly within Vinkius's ephemeral V8 sandbox. No inputs are cached, ensuring absolute privacy for your research data.

Build type-safe space science applications by validating NASA MCP Server responses instantly with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA MCP to Pydantic AI

Create your Vinkius account to connect NASA 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 with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Asteroid Telemetry at Runtime

The `get_neo_feed` tool outputs structured JSON containing asteroid sizes, velocities, and hazard ratings. When your Pydantic AI agent calls this tool, the framework enforces strict schema validation on the incoming NASA payload to prevent silent data corruption. If the API returns unexpected types or missing fields, the Pydantic AI framework raises a validation error immediately. This ensures your planetary defense tracking systems only process clean, reliable telemetry data.

Type-Safe Earth and Mars Imagery Queries

The `get_earth_imagery` tool requires exact coordinates and returns satellite imagery metadata. To verify rover operational statuses before pulling images, your Pydantic AI agent calls `get_mars_rovers` and parses the active cameras and last-photo dates. Consider this: every image URL, timestamp, and coordinate is parsed into a Pydantic model before your Pydantic AI agent ever sees it. You can then query `get_mars_photos` or pull whole-disk Earth views using `get_epic_images` with complete type safety.

Pydantic AI Parses Patent and Media Data

The `search_patents` tool retrieves federal patent records, abstracts, and licensing availability. To find accompanying software or media, your Pydantic AI agent uses `get_tech_transfer` and `search_nasa_library` to query public archives. Your Pydantic AI agent can also fetch daily educational content using `get_apod`. By using the unified MCPToolset class, you connect this MCP Server to your type-safe agent over secure HTTP or SSE transports.

Setup guide

Set up NASA 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-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NASA 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 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 MCP in Pydantic AI

Use the unified MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset into the toolsets argument of your Pydantic AI Agent constructor to register all nine tools.

Pydantic AI validates all incoming payloads at runtime. If a tool like get_neo_feed returns a malformed data structure, the framework raises a validation error, preventing your agent from hallucinating or acting on bad data.

Yes. The MCPToolset class natively handles both Streamable HTTP and SSE transports, allowing your agent to communicate with the MCP host running on the Vinkius infrastructure.

Yes, the get_mars_photos tool accepts camera parameters like MAST, MAHLI, or PANCAM. The tool returns structured schemas containing the photo URL, rover details, and Martian sol date.

Coordinate inputs for get_earth_imagery and search queries for search_patents are processed directly within Vinkius's ephemeral V8 sandbox. No inputs are cached, ensuring absolute privacy for your research data.

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