How to Use the NASA APOD — Astronomy Picture of the Day MCP in AutoGen

Q: How do I give my AutoGen agents access to the NASA APOD — Astronomy Picture of the Day tools?

After you pip install -U "autogen-extmcp", just call the mcpservertools function with your server's URL. This returns a tool list that you can pass directly to your AssistantAgent or UserProxyAgent when you create them.

Q: Do I need to write custom Python functions for each APOD tool?

No. The autogen-extmcp package does the work for you. The mcpservertools function inspects the MCP server, finds the available tools like getapod, and automatically creates the Python callables your agents need.

Build teams of AutoGen agents that debate and analyze NASA's APOD data to reach a consensus on complex astronomical queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA APOD — Astronomy Picture of the Day MCP to AutoGen

Create your Vinkius account to connect NASA APOD — Astronomy Picture of the Day 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 APOD — Astronomy Picture of the Day with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate APOD Findings

With AutoGen, you create a conversation. For example, set up an "Explorer" agent that uses `get_random_apod` to find interesting images from the archive. When it finds one, it presents it to a "Theorist" agent in the group chat. The Theorist agent can then use `get_apod_range` to search for related images from the same time period, looking for patterns or connections. They discuss the findings, challenge each other's ideas, and work toward a conclusion. You're not just running a command; you're observing a team of specialists at work.

Create Specialized Agent Roles

Design an agent team where each member has a specific job, defined by the tools you give them. A "Curator" agent could be responsible for calling `get_apod` each day and announcing the new picture. A "Historian" agent might only have access to `get_apod_range` to answer questions about past events. AutoGen lets these specialized agents talk to each other. The Curator can ask the Historian, "Have we seen a solar flare like this in the last five years?" The Historian does the research and reports back to the group. This MCP server makes it simple to equip each agent with just the NASA tools it needs for its role.

Your Personal MCP Server for AutoGen

Getting the NASA APOD tools into your agent conversation is simple. Just use the `mcp_server_tools` function from the AutoGen extension, point it at your server's URL, and you'll get back a list of tools ready for your `AssistantAgent`. The `McpToolAdapter` handles the schema conversion behind the scenes. You don't have to write any boilerplate code to connect to the API. You can get straight to designing the agent conversation and defining their roles, while the MCP server provides a reliable data feed from NASA.

Setup guide

Set up NASA APOD — Astronomy Picture of the Day 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 APOD — Astronomy Picture of the Day 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 APOD — Astronomy Picture of the Day_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NASA APOD — Astronomy Picture of the Day 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 APOD — Astronomy Picture of the Day_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NASA APOD — Astronomy Picture of the Day 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 APOD — Astronomy Picture of the Day 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 APOD — Astronomy Picture of the Day MCP in AutoGen

After you `pip install -U "autogen-ext[mcp]"`, just call the `mcp_server_tools` function with your server's URL. This returns a tool list that you can pass directly to your `AssistantAgent` or `UserProxyAgent` when you create them.

Yes, that's the core concept of AutoGen. You can have one agent use `get_random_apod` to propose research topics, and a second agent use `get_apod_range` to investigate those topics. They collaborate by sending messages and tool results back and forth in a chat.

When an agent decides to use a tool, AutoGen executes the call to the MCP server. The result, like the APOD image data and explanation, is then posted back into the conversation as a message. This allows the other agents to see the data and react to it.

No. The `autogen-ext[mcp]` package does the work for you. The `mcp_server_tools` function inspects the MCP server, finds the available tools like `get_apod`, and automatically creates the Python callables your agents need.

The only data sent is what's required for the tool call—a date, a range of dates, or a count for random images. Your Vinkius token handles authentication. Each request is an independent, ephemeral transaction, so no conversational history or agent state is sent to the Vinkius MCP server.

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