How to Use the NASA DONKI — Space Weather Intelligence MCP in CrewAI

Q: How do I add NASA DONKI — Space Weather Intelligence to my CrewAI agents?

Install the crewaitools package. You can pass the server URL directly into the mcps array on your agent definition. The agent will automatically discover all seven solar telemetry tools.

Q: How do I restrict certain agents to specific solar endpoints?

Use the MCPServerHTTP class and configure a toolfilter. You can limit your radiation expert agent to only access the radiation belt and energetic particle tools.

Deploy a specialized crew of AI agents to monitor, analyze, and act on severe space weather events using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA DONKI — Space Weather Intelligence MCP to CrewAI

Create your Vinkius account to connect NASA DONKI — Space Weather Intelligence to CrewAI 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 DONKI — Space Weather Intelligence with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Heliophysics Roles

The `get_solar_flares` tool feeds directly into a researcher agent tasked with monitoring C, M, and X-class events. CrewAI thrives on specialization. Instead of one overloaded prompt trying to understand the entire solar system, you assign a dedicated watcher to look for radio blackout triggers. When the researcher spots an X-class flare, it passes the context to an analyst agent. The analyst then queries `get_cme` to see if a coronal mass ejection accompanied the flare. This shared memory model means the second agent already knows the exact timestamp to look for.

Predict Geomagnetic Storms

Running `get_interplanetary_shocks` lets a forecaster agent track disturbances in the solar wind before they hit Earth. Sequential execution ensures the forecaster finishes its shockwave analysis before handing off to a mitigation agent. The crew builds a complete timeline of the incoming threat. The mitigation agent then uses `get_geomagnetic_storms` to check the Kp index. If it detects a Kp=9 extreme storm, it can autonomously draft warnings for power grid operators. The agents collaborate to turn raw shock data into actionable survival protocols.

Parse the Notification Feed via MCP

Polling `get_donki_notifications` acts as the perfect trigger for a manager agent in a hierarchical setup. The manager scans the unified feed of CMEs, shocks, and radiation events. When it sees something dangerous, it delegates specific investigation tasks to subordinate agents. One worker might check `get_solar_energetic_particles` for astronaut safety, while another evaluates `get_radiation_belt` for satellite risks. The MCP protocol handles the tool execution seamlessly in the background. The manager compiles their findings into a single executive briefing.

Setup guide

Set up NASA DONKI — Space Weather Intelligence MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke NASA DONKI — Space Weather Intelligence tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="NASA DONKI — Space Weather Intelligence Analyst",
    goal="Access and analyze NASA DONKI — Space Weather Intelligence data via MCP.",
    backstory="Expert analyst with direct NASA DONKI — Space Weather Intelligence access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent NASA DONKI — Space Weather Intelligence transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="NASA DONKI — Space Weather Intelligence Analyst",
        goal="Access and analyze NASA DONKI — Space Weather Intelligence data via MCP.",
        backstory="Expert analyst with direct NASA DONKI — Space Weather Intelligence access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent NASA DONKI — Space Weather Intelligence transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 DONKI — Space Weather Intelligence 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 DONKI — Space Weather Intelligence MCP in CrewAI

Install the crewai[tools] package. You can pass the server URL directly into the mcps array on your agent definition. The agent will automatically discover all seven solar telemetry tools.

Yes. CrewAI uses shared memory. If your researcher agent pulls a Kp index, the analyst agent can read that exact value without having to query the endpoint a second time.

The framework supports stdio, SSE, and Streamable HTTP. For continuous monitoring of space weather, SSE provides a highly reliable connection for your autonomous teams.

Use the MCPServerHTTP class and configure a tool_filter. You can limit your radiation expert agent to only access the radiation belt and energetic particle tools.

Yes. The connection isolates your crew's internal deliberations from the outside world. The server only receives requests for Kp indices and shockwave timestamps. Your proprietary agent instructions and internal task assignments never leave your secure environment.

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