How to integrate Ambee MCP with CrewAI

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

Introduction

This guide walks you through connecting Ambee to CrewAI using the Composio tool router. By the end, you'll have a working Ambee agent that can show today's air quality for paris, get wildfire risk forecast for california, retrieve pollen count by my zip code, list recent natural disasters in asia through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Ambee account through Composio's Ambee 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 Ambee connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Ambee
  • Build a conversational loop where your agent can execute Ambee 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 Ambee MCP server, and what's possible with it?

The Ambee MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ambee account. It provides structured and secure access to hyperlocal environmental data, so your agent can perform actions like retrieving real-time air quality, fetching pollen and weather updates, forecasting wildfire risk, and monitoring natural disasters on your behalf.

  • Hyperlocal air quality monitoring: Instantly get real-time air quality data for any city, postal code, or precise geographic coordinates to stay informed about pollution and AQI levels in your area.
  • Air quality forecasting: Ask your agent to predict air quality trends up to 48 hours in advance for specific locations, helping you plan outdoor activities with health in mind.
  • Wildfire risk assessment: Access weekly wildfire risk forecasts for targeted places, so you can stay aware of environmental hazards before they happen.
  • Disaster and incident tracking: Retrieve the latest natural disaster data by continent, keeping you updated about major environmental events worldwide.
  • Geocoding and location resolution: Effortlessly transform city names or addresses into latitude and longitude coordinates, making location-based queries accurate and seamless for your agent.

Supported Tools & Triggers

Tools
Get Air Quality by CityTool to retrieve real-time air quality data for a specific city.
Get Air Quality by Latitude and LongitudeTool to retrieve real-time air quality data for a specific latitude and longitude.
Get Air Quality Forecast by Latitude and LongitudeTool to retrieve air quality forecast for a specific latitude and longitude.
Get Wildfire Risk Forecast by PlaceTool to retrieve wildfire risk forecast for a specific place.
Geocode by PlaceTool to transform a place name or address into geographic coordinates.
Get Air Quality by CityTool to retrieve real-time air quality data for a specific city.
Get Air Quality by Country CodeTool to retrieve real-time air quality data for a specific country using a 3-letter iso code.
Get Air Quality by Latitude and LongitudeTool to retrieve real-time air quality data for a specific latitude and longitude.
Get Air Quality by Postal CodeTool to retrieve real-time air quality data for a specific postal code and country.
Retrieve latest natural disasters by continentTool to retrieve latest natural disaster data for a specific continent.
Get Elevation by Latitude and LongitudeTool to retrieve elevation statistics (min, max, mean) for a specific latitude and longitude.
Get Elevation by PlaceTool to retrieve elevation or altitude data for a specific location by place name.
Get ILI Forecast by Latitude and LongitudeTool to retrieve 30-day forecast of influenza-like illness (ili) risk using latitude and longitude.
Get Wildfire Data by Latitude and LongitudeTool to retrieve real-time wildfire data for a specific latitude and longitude.
Get Wildfire Data by PlaceTool to retrieve real-time wildfire data for a specific place.
Get Wildfire Risk Forecast by PlaceTool to retrieve wildfire risk forecast for a specific place.

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 Ambee 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 Ambee 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 Ambee MCP URL

Create a Composio Tool Router session for Ambee

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["ambee"],
)
url = session.mcp.url
What's happening:
  • You create a Ambee only session through Composio
  • Composio returns an MCP HTTP URL that exposes Ambee 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="Ambee Assistant",
    goal="Help users interact with Ambee through natural language commands",
    backstory=(
        "You are an expert assistant with access to Ambee tools. "
        "You can perform various Ambee 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 Ambee 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 Ambee 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 Ambee 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_ambee_agent.py

Complete Code

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

python
# file: crewai_ambee_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 Ambee session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["ambee"],
    )
    url = session.mcp.url

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

    # Create Ambee assistant agent
    toolkit_agent = Agent(
        role="Ambee Assistant",
        goal="Help users interact with Ambee through natural language commands",
        backstory=(
            "You are an expert assistant with access to Ambee tools. "
            "You can perform various Ambee 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 Ambee 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 Ambee 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 Ambee through Composio's Tool Router. The agent can perform Ambee 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 Ambee MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Ambee MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Ambee MCP with Claude Agent SDK

Google ADK

Google ADK

Use Ambee MCP with Google ADK

LangChain

LangChain

Use Ambee MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Ambee MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Ambee MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Ambee MCP with LlamaIndex

FAQ

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

With a standalone Ambee MCP server, the agents and LLMs can only access a fixed set of Ambee tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Ambee 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 Ambee tools.

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

Yes, absolutely. You can configure which Ambee 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 Ambee 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