How to Use the NASA Full — Ultimate Space Intelligence MCP in LangChain

Q: How do I use NASA Full — Ultimate Space Intelligence to build a planetary defense agent with LangChain?

Start by giving your agent access to getcloseapproaches and getneolookup. You can create a chain where the agent checks for new, potentially hazardous asteroids daily, then uses the lookup tool to gather more data on any high-risk objects it finds.

Build autonomous space intelligence agents that chain NASA API calls with LangChain. Your agent decides the next step.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA Full — Ultimate Space Intelligence MCP to LangChain

Create your Vinkius account to connect NASA Full — Ultimate Space Intelligence to LangChain 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 Full — Ultimate Space Intelligence with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain NASA APIs for Multi-Step Analysis

This is where LangChain shines. An agent can get a list of upcoming asteroid flybys with `get_close_approaches`, then decide on its own to use `get_neo_lookup` on the most interesting one to get its full orbital details. It’s a two-step analysis, with zero hard-coded logic. You build the reasoning pipeline, not just the API call. Connect a solar flare alert from `get_solar_flares` directly to a check on `get_radiation_belt` activity. The agent links cause and effect by chaining the tools together in real time.

Build Custom Space Weather Dashboards with this MCP Server

Give your agent a goal, like 'give me a morning brief on space weather.' Using a ReAct framework, it will intelligently pick the right tools for the job. It might start with `get_donki_notifications` for a broad look, then dig deeper into specific events using `get_cme` or `get_geomagnetic_storms`. This isn't a static report. The agent assembles the data on the fly, based on what the APIs return. If a major X-class flare is reported by `get_solar_flares`, it knows to check for related interplanetary shocks. You get a dynamic summary, not a fixed dashboard.

Explore Mars and Beyond, Step by Step

Don't just fetch a random Mars photo. Build an agent that explores methodically. It can start by pulling the mission summary with `get_mars_manifest` to see what cameras and dates are available for the Curiosity rover. From there, it can pull all photos from a specific camera using `get_mars_photos`. You define the goal, and the agent figures out the steps. It can even search for habitable exoplanets with `get_habitable_zone`, then cross-reference the results against the full database with `query_confirmed_planets` to get mass and temperature data. One tool's output becomes the next tool's input.

Setup guide

Set up NASA Full — Ultimate Space Intelligence MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NASA Full — Ultimate Space Intelligence tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "nasa-full-ultimate-space-intelligence-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NASA Full — Ultimate Space Intelligence transactions"
    })
    print(result["messages"][-1].content)

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 Full — Ultimate Space 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 Full — Ultimate Space Intelligence MCP in LangChain

Start by giving your agent access to `get_close_approaches` and `get_neo_lookup`. You can create a chain where the agent checks for new, potentially hazardous asteroids daily, then uses the lookup tool to gather more data on any high-risk objects it finds.

Yes. LangChain is designed for this. You can create a tool for your internal database and give it to the agent alongside the 32 NASA tools. The agent can then answer questions by pulling data from both sources in the same chain.

Use an agent that can choose from a list of tools, like a ReAct or OpenAI Functions agent. The key is to have great tool descriptions—which we've already written. The agent will read the descriptions to decide whether `get_mars_photos` or `get_mars_photos_by_date` is the right choice for the user's request.

Modern LLMs can handle dozens of tools, so all 32 are well within limits. The performance depends more on the quality of the tool descriptions and the complexity of the agent's reasoning task than the raw number of tools.

None. The server only interacts with public NASA data like asteroid trajectories and image metadata. Vinkius processes each of your agent's requests in a stateless, ephemeral sandbox. No personal data is involved, and no session information is ever stored.

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