How to Use the NASA MCP in AutoGen

Q: How do I initialize the NASA tools in AutoGen?

Install autogen-extmcp. Use mcpservertools with a StreamableHttpServerParams pointing to the endpoint, then pass that list to your AssistantAgent constructor.

Q: Does AutoGen require manual schema mapping for these MCP tools?

No. McpToolAdapter automatically converts the standard tool definitions into the exact format your conversational agents require.

Build AutoGen conversational agents that debate space policy and analyze NASA datasets.

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 AutoGen

Create your Vinkius account to connect NASA 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 with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate asteroid threats via AutoGen

Executing `get_neo_feed` via the MCP Server gives your multi-agent setup hard numbers on asteroid diameters and velocities. A risk-assessment agent pulls the seven-day feed, while a secondary policy agent reviews the findings to debate whether any objects qualify as hazardous. They don't just execute commands blindly. The agents negotiate the interpretation of the data. One argues a specific trajectory requires attention, prompting the other to call `get_earth_imagery` to check potential impact zones.

Cross-examine aerospace patents

Your agents use `search_patents` to pull commercialization records and argue over technology viability. An engineering persona fetches the patent abstract, and a business persona challenges the licensing availability. This consensus-driven approach filters out bad ideas. Instead of a single LLM spitting out a summary, you get a documented conversation where the MCP Server provides the factual baseline for their dispute.

Verify rover timelines

Calling `get_mars_rovers` allows an oversight agent to check which machines are currently active on the surface. If a research agent requests photos from a specific sol, the oversight agent verifies the timeline before approving the `get_mars_photos` call. You set up a system of checks and balances. The framework handles the schema conversion automatically, letting your specialized agents focus entirely on the scientific debate.

Setup guide

Set up NASA 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 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_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NASA 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_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NASA 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 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 AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with a `StreamableHttpServerParams` pointing to the endpoint, then pass that list to your `AssistantAgent` constructor.

Yes. You provide the tool list to specific agents in your group chat. The science agent gets access to the space feeds, while the summarization agent just reads their conversation.

The tool call fails or returns empty results. A critic agent spots this failure in the chat history and instructs the first agent to try a different search query.

No. `McpToolAdapter` automatically converts the standard tool definitions into the exact format your conversational agents require.

The endpoint processes patent search terms, camera types, and dates. We run the connection through an ephemeral sandbox, guaranteeing your multi-agent debate history never persists on our infrastructure.

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