How to Use the NASA Mars — Rover Photos from the Red Planet MCP in Vercel AI SDK

Q: How do I connect the NASA Mars — Rover Photos from the Red Planet MCP Server to Vercel AI SDK?

Run npm install ai @ai-sdk/mcp in your project. Then instantiate createMCPClient with your HTTP transport URL and pass the resulting tools to streamText.

Q: Can Vercel AI SDK stream images from NASA Mars — Rover Photos from the Red Planet?

Yes. Your AI agent calls getmarsphotos and returns the raw image URLs. You map those URLs to standard image components in your React or Vue frontend while the text streams.

Stream raw Martian surface images directly into your React and Next.js frontends using this Vercel AI SDK MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA Mars — Rover Photos from the Red Planet MCP to Vercel AI SDK

Create your Vinkius account to connect NASA Mars — Rover Photos from the Red Planet to Vercel AI 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 Mars — Rover Photos from the Red Planet with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Vercel AI SDK data live from Mars

The `get_mars_latest` tool pulls the absolute newest images beamed back from Curiosity directly into your user's browser. When your AI client executes this tool, Vercel AI SDK streams the resulting image URLs and telemetry straight to your React frontend. Users watch the Martian surface appear instantly without waiting for a loading spinner. You do not have to write custom polling logic to check if NASA uploaded new shots. Your agent fetches the latest payloads natively. It renders the FHAZ and RHAZ camera feeds as fast as the HTTP transport delivers them.

Map mission manifests instantly

The `get_mars_manifest` tool gives your edge functions the exact active sol ranges for Curiosity, Opportunity, and Spirit. Your AI agent reads this manifest first to understand exactly which dates actually contain valid image data. This prevents your application from sending dead queries to the NASA API. Passing this context back through the Vercel AI SDK means your UI can dynamically disable invalid date pickers. The user only clicks dates where rover data actually exists.

Fetch historical archives by Earth date

The `get_mars_photos_by_date` tool translates standard Earth calendar dates into Martian sol queries automatically. Your Next.js app takes a standard date input, passes it to the AI, and the agent executes the tool to grab that day's specific MAST or NAVCAM shots. If your user wants to see what Opportunity saw on a specific Tuesday in 2008, the agent handles the conversion. The resulting 800,000+ photo archive becomes completely searchable through natural language in your web application.

Setup guide

Set up NASA Mars — Rover Photos from the Red Planet MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all NASA Mars — Rover Photos from the Red Planet tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent NASA Mars — Rover Photos from the Red Planet transactions",
});

console.log(text);
await mcpClient.close();

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 Mars — Rover Photos from the Red Planet 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 Mars — Rover Photos from the Red Planet MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp` in your project. Then instantiate `createMCPClient` with your HTTP transport URL and pass the resulting tools to `streamText`.

Yes. Your AI agent calls `get_mars_photos` and returns the raw image URLs. You map those URLs to standard image components in your React or Vue frontend while the text streams.

The server handles the NASA rate limits natively. Your edge functions just request the data, and the server manages the connection to the raw telemetry endpoints.

Just tell your AI prompt to look for specific camera strings. The agent passes that string into the `get_mars_photos` parameters before returning the results to your UI.

This server only reads public space telemetry, mission manifests, and raw Martian images. No user data flows backward to NASA. The connection requires a single endpoint token, keeping your frontend architecture strictly zero-trust.

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