How to integrate Nasa MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Nasa Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Nasa to CrewAI using the Composio tool router. By the end, you'll have a working Nasa agent that can show me mars rover photos from curiosity on sol 1000, list recent natural disaster events worldwide, find all eonet event categories available, search nasa science data collections for climate datasets through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Nasa account through Composio's Nasa MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Nasa connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Nasa
  • Build a conversational loop where your agent can execute Nasa operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

What is the Nasa MCP server, and what's possible with it?

The Nasa MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to NASA's public data APIs. It provides structured and secure access to a wealth of Earth science, planetary, and event data, so your agent can search datasets, fetch Mars rover photos, explore natural events, and visualize scientific information on your behalf.

  • Search NASA science data collections: Empower your agent to query and filter massive datasets from the Common Metadata Repository (CMR) by spatial, temporal, or metadata criteria.
  • Retrieve Mars rover imagery: Ask your agent to fetch stunning photos captured by Mars rovers for specific Martian days, enabling research and exploration right from your workflow.
  • Monitor natural events worldwide: Let your agent pull up-to-date lists of global natural events—like wildfires, storms, or volcanic activity—using NASA's EONET feeds in ATOM or RSS formats.
  • Visualize and analyze event categories and layers: Direct your agent to explore available data layers and event categories for advanced event visualization and filtering in scientific research.
  • Access detailed event source and magnitude data: Have your agent retrieve metadata about event sources and magnitudes, making it easier to understand the context and scale of natural phenomena tracked by NASA.

Supported Tools & Triggers

Tools
Get CMR CollectionsTool to retrieve collections from the common metadata repository (cmr).
Get CMR GranulesTool to retrieve granules from the common metadata repository (cmr).
Get EONET CategoriesTool to retrieve a list of all event categories from eonet.
Get EONET Events (ATOM)Tool to retrieve a list of natural events in atom format.
Get EONET Events RSSTool to retrieve a list of natural events in rss format.
Get EONET LayersTool to retrieve available data layers for event visualization.
GET EONET MagnitudesTool to retrieve a list of available event magnitudes and their descriptions.
GET EONET Source by IDTool to retrieve details for a specific eonet event source by id.
Get EONET SourcesTool to retrieve a list of event sources.
Get Mars Rover PhotosTool to fetch photos taken by a specified mars rover on a given martian sol.
Search Near Earth ObjectsTool to search near-earth objects by closest approach date range.
Search SVS VisualizationsTool to search for visualizations in the scientific visualization studio (svs).

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Nasa connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Nasa via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Nasa MCP URL

Create a Composio Tool Router session for Nasa

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["nasa"],
)
url = session.mcp.url
What's happening:
  • You create a Nasa only session through Composio
  • Composio returns an MCP HTTP URL that exposes Nasa tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Nasa Assistant",
    goal="Help users interact with Nasa through natural language commands",
    backstory=(
        "You are an expert assistant with access to Nasa tools. "
        "You can perform various Nasa operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Nasa MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Nasa operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Nasa related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_nasa_agent.py

Complete Code

Here's the complete code to get you started with Nasa and CrewAI:

python
# file: crewai_nasa_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Nasa session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["nasa"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Nasa assistant agent
    toolkit_agent = Agent(
        role="Nasa Assistant",
        goal="Help users interact with Nasa through natural language commands",
        backstory=(
            "You are an expert assistant with access to Nasa tools. "
            "You can perform various Nasa operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Nasa operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Nasa related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Nasa through Composio's Tool Router. The agent can perform Nasa operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Nasa MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Nasa MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Nasa MCP with Claude Agent SDK

Google ADK

Google ADK

Use Nasa MCP with Google ADK

LangChain

LangChain

Use Nasa MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Nasa MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Nasa MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Nasa MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Nasa MCP?

With a standalone Nasa MCP server, the agents and LLMs can only access a fixed set of Nasa tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Nasa and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Nasa tools.

Can I manage the permissions and scopes for Nasa while using Tool Router?

Yes, absolutely. You can configure which Nasa scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Nasa data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free