How to Use the NASA MCP in OpenAI Agents SDK

Q: How does the agent know which Mars rover to query?

The agent first calls getmarsrovers to see which rovers are active and check their last active dates. It uses that metadata to construct precise queries for getmarsphotos.

Q: How is my search query and location data secured?

Vinkius processes all coordinate inputs for getearthimagery and text strings for searchpatents inside an isolated V8 sandbox. No raw query data or geographic coordinates are stored or shared outside the active session.

Run production-grade space exploration workflows by connecting the NASA MCP Server directly to your OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect NASA to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Near-Earth Asteroids Automatically

The `get_neo_feed` tool retrieves real-time data on asteroids approaching Earth, including their estimated diameters, velocity, and hazard status. Your OpenAI Agents SDK queries this feed using a start and end date window of up to seven days. It feeds raw orbital telemetry straight into your decision-making pipelines. Because the MCP standard demands strict guardrails, this dataset lets you build automated collision alerts. The OpenAI Agents SDK validates these NASA telemetry payloads before executing downstream actions, keeping your monitoring systems accurate and secure.

OpenAI Agents SDK Visualizes Earth and Mars

The `get_mars_photos` tool fetches actual imagery captured by Mars rovers, filtered by specific cameras like MAST or PANCAM and Martian sol dates. To find out which rovers are currently active and when they last transmitted data, your OpenAI Agents SDK calls `get_mars_rovers` first. For Earth-side observation, your OpenAI Agents SDK uses `get_earth_imagery` to retrieve satellite pictures based on exact latitude and longitude coordinates. You can also pull whole-disk Earth views via `get_epic_images` to monitor atmospheric patterns over time.

Search Federal Tech Transfer and Patents

The `search_patents` tool queries NASA's active patent database to find licensing opportunities, abstracts, and patent numbers. To cross-reference these patents with commercialization initiatives, your OpenAI Agents SDK uses `get_tech_transfer` to pull descriptions and contact info. This MCP Server also supports broader research via `search_nasa_library` for media assets, and `get_apod` for daily astronomy imagery. Right. So. Running these tools inside an async context manager ensures your OpenAI Agents SDK handles high-throughput queries without dropping connections.

Setup guide

Set up NASA MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NASA tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NASA tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NASA tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NASA Agent",
            instructions="You have access to NASA tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package and initialize MCPServerStreamableHttp with your Vinkius connection URL. Pass this server instance in the mcp_servers list when instantiating your Agent. The SDK auto-discovers all nine tools instantly.

Yes. Set cacheToolsList to True in your SDK parameters to prevent redundant tool discovery calls. This reduces unnecessary overhead when your agent repeatedly queries tools like get_neo_feed or get_apod.

Yes, the SDK natively supports async context managers. Your agent can run multiple image queries via get_earth_imagery and get_epic_images concurrently without blocking the main event loop.

The agent first calls get_mars_rovers to see which rovers are active and check their last active dates. It uses that metadata to construct precise queries for get_mars_photos.

Vinkius processes all coordinate inputs for get_earth_imagery and text strings for search_patents inside an isolated V8 sandbox. No raw query data or geographic coordinates are stored or shared outside the active session.

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