How to Use the ESA Near Earth Objects MCP in Google ADK

Q: Can I restrict which ESA Near Earth Objects tools the Google ADK exposes?

Absolutely. Use the toolnames filter in your setup to only expose specific endpoints. You might want to limit the agent to just pulling priority targets to save tokens.

Feed raw ESA Near Earth Objects data straight into Gemini using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ESA Near Earth Objects MCP to Google ADK

Create your Vinkius account to connect ESA Near Earth Objects 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 ESA Near Earth Objects with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query the MCP Server for Impact Probabilities

`get_impact_table` feeds virtual impactor dates and Palermo Scale values directly to your Gemini agent. This MCP Server integration lets you dump thousands of rows of threat data into Gemini's massive context window. The agent processes the entire board at once rather than chunking it. You can pipe this output straight into BigQuery. Run `get_risk_list` to grab the estimated diameters and Torino Scale ratings for actively monitored rocks. Gemini maps the JSON response, structures it, and logs it to your data warehouse for historical tracking.

Cross-Reference Past and Future Flybys

`get_recent_close_approaches` pulls the data on asteroids that just buzzed Earth. You use this to validate past orbital predictions against actual telemetry. Your agent compares the miss distance and velocity against the original projections to calculate error margins. Combine that with `get_upcoming_close_approaches` to forecast the next few weeks. Gemini can hold both datasets in memory and spot patterns in the ESA Space Safety programme updates. You get a clear view of traffic in our immediate orbital neighborhood.

Analyze Physical and Orbital Properties

`get_object_orbital_elements` grabs the essential math for trajectory computation. This is not a summary of the orbit. It provides the raw orbital parameters required to map an asteroid's path through the solar system. Pair it with `get_object_physical_properties` to calculate actual kinetic threat. Gemini takes the physical diameter, albedo, and velocity, then runs the math. If the object is on the `get_special_risk_list`, your agent automatically flags it for priority review.

Setup guide

Set up ESA Near Earth Objects 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 ESA Near Earth Objects 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="ESA Near Earth Objects_agent",
    model="gemini-2.0-flash",
    instruction="You have access to ESA Near Earth Objects 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 ESA NEOCC. 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 ESA Near Earth Objects 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 ESA Near Earth Objects MCP in Google ADK

Initialize McpToolset using StreamableHttpServerParameters with your specific URL. Pass this toolset into your LlmAgent configuration.

Absolutely. Use the tool_names filter in your setup to only expose specific endpoints. You might want to limit the agent to just pulling priority targets to save tokens.

Gemini's 1M+ token window easily absorbs the output from the full NEA list. You can load all known near-Earth asteroid designations at once without truncating the prompt.

The ESA Space Safety programme updates the database multiple times a day. Your agent fetches the live state every time it triggers the tool.

Your Google Cloud credentials never touch the external endpoint. The MCP protocol strictly isolates the orbital parameters and visual magnitude data, allowing Gemini to process the JSON response within your VPC before writing to BigQuery.

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