How to Use the NASA MCP in Google ADK

Q: What details do the Mars rover tools provide?

The getmarsrovers tool returns active operational status and last photo dates. Once your agent has this, it queries getmarsphotos using specific camera filters like MAST or NAVCAM to get precise images.

Q: What happens to the coordinates and search terms I send?

Every latitude, longitude, and search string sent to getearthimagery or searchnasalibrary goes through an encrypted ephemeral transit. Vinkius executes the request in a zero-trust environment, leaving no persistent log of your geographic queries.

Feed real-time NASA telemetry directly into Google ADK pipelines for long-context reasoning and BigQuery analysis.

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 Google ADK

Create your Vinkius account to connect NASA to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Planetary Defense Data with Google ADK

The `get_neo_feed` tool provides daily asteroid counts, velocity metrics, and hazard classifications for objects near Earth. Your Google ADK agent pulls this telemetry directly into the Gemini long-context window to analyze orbital trends over time. By feeding this NASA data into your Google Cloud environment, you can join asteroid trajectories with existing datasets in BigQuery. The MCP Server handles the connection, letting your Google ADK agent run complex calculations on planetary defense data.

Query Geographic Changes Using Earth Imagery

The `get_earth_imagery` tool retrieves historical satellite images of specific coordinates to analyze geographic shifts. To get wider planetary perspectives, your Google ADK agent calls `get_epic_images` to fetch full-disk, enhanced-color views of Earth. These tools allow your Google ADK agent to monitor environmental changes, deforestation, or urban growth. Google ADK handles the transport, feeding these high-resolution NASA image URLs straight into Vertex AI vision models for automated analysis.

Access NASA Patents and Media Archives

The `search_patents` tool searches government patent records, returning titles, abstracts, and licensing availability. For broader research, your Google ADK agent uses `get_tech_transfer` to find commercial software listings and `search_nasa_library` to locate educational media. You can also retrieve the Astronomy Picture of the Day using `get_apod` to populate visual dashboards. This setup uses the McpToolset class to expose these tools to your Google ADK agent with minimal configuration.

Setup guide

Set up NASA MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with NASA tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="NASA_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NASA tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate McpToolset with the Vinkius server HTTP parameters. Pass this toolset directly into your LlmAgent constructor to expose all nine space and Earth science tools to your model.

Yes. You can pass a filtered list of tool names to your McpToolset configuration. This prevents the agent from calling tools like search_patents if you only want it focusing on get_earth_imagery.

The tools return image URLs and metadata rather than raw binary data. Your agent reads the URLs from get_epic_images or get_mars_photos and passes them to Gemini models, which leverage their massive context windows to process the images.

The get_mars_rovers tool returns active operational status and last photo dates. Once your agent has this, it queries get_mars_photos using specific camera filters like MAST or NAVCAM to get precise images.

Every latitude, longitude, and search string sent to get_earth_imagery or search_nasa_library goes through an encrypted ephemeral transit. Vinkius executes the request in a zero-trust environment, leaving no persistent log of your geographic queries.

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