How to Use the NASA MCP in LangChain

Q: How do I connect the NASA MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. You initialize a MultiServerMCPClient pointing to the NASA endpoint and pass the resulting tools to your agent.

Q: Does the server support pagination for media searches?

The searchnasalibrary tool accepts page numbers. Your custom agent loop increments this parameter to scrape multiple pages of results automatically.

Build multi-step reasoning pipelines using LangChain to query NASA's universe of data.

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 LangChain

Create your Vinkius account to connect NASA 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 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain NASA MCP Server queries

LangChain agents execute `search_patents` to pull aerospace technology records straight from the source. You build a ReAct agent that grabs a patent, reads the abstract, and decides if it needs to query an external vector store for similar commercial applications. The real advantage here is observability. Every time your chain hits the endpoint, LangSmith logs the exact inputs and latency. If an agent loops endlessly trying to parse `get_tech_transfer` categories, you spot the failure instantly in the trace.

Feed rover images to vision nodes

Use `get_mars_photos` to feed visual data directly into your LangChain pipeline. Your agent decides which rover to query, grabs the raw URL, and passes it down the chain to a separate vision model for crater analysis. This goes beyond fetching static data. You build autonomous workflows. The agent checks `get_mars_rovers` to confirm active status, then dynamically adjusts its next tool call to pull yesterday's images without human intervention.

Cross-reference orbital events

LangChain MCP Server integrations let your agent cross-reference space events using `get_neo_feed`. It pulls a list of potentially hazardous asteroids passing Earth this week and formats the velocities into a clean markdown table. Output from one operation becomes the input for the next. The agent takes a specific asteroid date from the feed and immediately calls `get_earth_imagery` to see what the planet's cloud cover looked like that exact day.

Setup guide

Set up NASA 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 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-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 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 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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. You initialize a `MultiServerMCPClient` pointing to the NASA endpoint and pass the resulting tools to your agent.

Yes. You give the agent the tool list. It reads the descriptions and chooses whether to pull today's APOD or search the media library based on the user's prompt.

Chains let you build logic around the data. You pull an asteroid feed, pass it to an LLM for analysis, and save the result to a database in one continuous workflow.

The `search_nasa_library` tool accepts page numbers. Your custom agent loop increments this parameter to scrape multiple pages of results automatically.

The server processes coordinates, dates, and search queries for public space imagery and patents. Vinkius runs this in an ephemeral V8 Isolate Sandbox, meaning your agent's query parameters vanish the second the connection drops.

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