How to Use the NASA Open Data MCP in AutoGen

Q: How can I use AutoGen and the NASA Open Data server to get a more reliable answer?

You can create multiple agents. Have one agent call getsolarflares and another call getcoronalmassejections. A third "Validator" agent can then ask them to cross-reference their findings to confirm a space weather event before alerting you.

Launch a team of AutoGen agents to debate and analyze NASA data from multiple angles.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA Open Data MCP to AutoGen

Create your Vinkius account to connect NASA Open Data to AutoGen 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 Open Data with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up Agents to Debate Space Data

Go beyond simple tool execution. With AutoGen, you can create a group of agents that collaborate on NASA data. For instance, have one agent pull a list of asteroids with `get_near_earth_objects_feed` while a "RiskAnalyst" agent uses `lookup_asteroid` to check each one's potential hazard data. The magic is in the conversation. The agents can challenge each other's findings, ask for clarification, and reach a consensus before reporting back to you. This surfaces nuances that a single agent might miss, like correlating a CME event from `get_coronal_mass_ejections` with a simultaneous reading from `get_solar_flares`.

Your AutoGen MCP Server for Mission Control

Create a simulated mission control team. An "Imaging" agent could be responsible for fetching pictures using `get_earth_polychromatic_images` and `get_mars_rover_photos`. A "Science" agent could analyze the `get_astronomy_picture` of the day for educational content. A "Director" agent oversees them all. This multi-agent approach is perfect for complex, open-ended tasks. Instead of giving a rigid script, you give a high-level goal like "Prepare a report on Martian geology from the Curiosity rover's last 50 sols." The agents will coordinate using the available MCP tools to assemble the report.

Build Consensus on Ambiguous Data

Space data can be complex. What does a "potentially hazardous" asteroid classification really mean? Your agents can debate it. One agent might fetch the raw data with `lookup_asteroid`, another might look for context online, and a third could summarize the debate for a human expert. This is how you handle uncertainty. By having agents represent different viewpoints—for example, one focused on raw telemetry and another on public communication—you build a system that provides more balanced and well-reasoned outputs. It's a powerful way to use this NASA MCP server for more than just data retrieval.

Setup guide

Set up NASA Open Data MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes NASA Open Data tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="NASA Open Data_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NASA Open Data data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="NASA Open Data_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NASA Open Data data")
    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 Open Data 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 Open Data MCP in AutoGen

You can create multiple agents. Have one agent call `get_solar_flares` and another call `get_coronal_mass_ejections`. A third "Validator" agent can then ask them to cross-reference their findings to confirm a space weather event before alerting you.

Yes. You can create specialized agents in AutoGen. You could give one agent access only to `get_mars_rover_photos` and another agent access only to the space weather tools, forcing them to collaborate to solve a problem.

An "Analyst" agent might say, "I found a near-Earth object with `get_near_earth_objects_feed`." A "Critic" agent could respond, "Is it hazardous? Use `lookup_asteroid` to check its threat level." This back-and-forth continues until they reach a conclusion.

Definitely. You could have agents plan a simulated Mars rover mission. One agent uses `get_mars_rover_manifest` to check operational parameters, while another uses `get_mars_rover_photos` to "scout" a location.

Your agents interact with public space data—specifically Near-Earth Object feeds and Mars rover mission manifests. Security is handled by the Vinkius platform's zero-trust architecture. Each tool call through the MCP server is an isolated, authenticated transaction, and the server does not store your session data.

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