How to integrate Datadog MCP with CrewAI

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

Introduction

This guide walks you through connecting Datadog to CrewAI using the Composio tool router. By the end, you'll have a working Datadog agent that can create downtime for nightly maintenance window, list all monitors tracking cpu usage, create synthetic api test for login endpoint, get details of production dashboard through natural language commands.

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

The Datadog MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Datadog account. It provides structured and secure access to your monitoring and observability platform, so your agent can perform actions like creating dashboards, managing monitors, scheduling downtimes, and tracking key events on your behalf.

  • Custom dashboard creation and management: Direct your agent to build new dashboards or retrieve detailed information about existing dashboards for unified infrastructure and application monitoring.
  • Monitor setup and deletion: Easily have your agent create new monitors to track critical metrics or remove outdated ones to keep your alerting system relevant.
  • Automated downtime scheduling: Let your agent schedule maintenance windows by creating downtimes that suppress alerts during planned outages or deployments.
  • Event tracking and logging: Ask your agent to create and log significant events—like deployments or configuration changes—so your team always stays informed.
  • Service level objectives and synthetic testing: Instruct your agent to define SLOs or set up synthetic API tests for continuous reliability and performance tracking.

Supported Tools & Triggers

Tools
Create DashboardCreate a dashboard in datadog.
Create downtimeCreates a new downtime in datadog to suppress alerts during maintenance windows or planned outages.
Create eventCreates a new event in datadog.
Create monitorCreates a new datadog monitor to track metrics, logs, or other data sources with configurable alerting thresholds and notifications.
Create SLOCreate a service level objective (slo) in datadog.
Create Synthetic API TestCreate a synthetic api test in datadog.
Create WebhookCreate a webhook in datadog.
Delete DashboardDelete a dashboard in datadog.
Delete monitorDeletes a datadog monitor permanently.
Get DashboardGet a specific dashboard from datadog.
Get monitorRetrieves detailed information about a specific datadog monitor, including its current state, configuration, and any active downtimes.
Get Service DependenciesGet service dependency mapping from datadog apm.
Get Synthetics LocationsTool to retrieve all available public and private locations for synthetic tests in datadog.
Get host tagsRetrieves all tags associated with a specific host in datadog.
Get Trace by IDGet detailed information about a specific trace by its id.
Get usage summaryRetrieves usage summary information from datadog including api calls, hosts, containers, and other billable usage metrics.
List All TagsList all tags from datadog.
List API KeysList api keys in datadog.
List APM ServicesList apm services from datadog.
List AWS IntegrationList aws integrations in datadog.
List dashboardsLists all datadog dashboards with basic information.
List eventsLists events from datadog within a specified time range.
List hostsLists all hosts in your datadog infrastructure with detailed information including metrics, tags, and status.
List IncidentsList incidents from datadog.
List Log IndexesTool to retrieve a list of all log indexes configured in datadog.
List monitorsGet all monitor details.
List RolesList roles from datadog organization.
List service checksLists service checks from datadog.
List SLOsList service level objectives (slos) from datadog.
List Synthetics TestsList synthetics tests from datadog.
List UsersList users from datadog organization.
List WebhooksList webhooks from datadog.
Mute MonitorMute a monitor in datadog.
Query metricsQueries datadog metrics and returns time series data.
Search logsSearches datadog logs with advanced filtering capabilities.
Search Spans AnalyticsSearch and analyze span data with aggregations in datadog.
Search TracesSearch for traces in datadog apm.
Submit metricsSubmits custom metrics to datadog.
Unmute MonitorUnmute a monitor in datadog.
Update DashboardUpdate a dashboard in datadog.
Update host tagsUpdates tags for a specific host in datadog.
Update monitorUpdates an existing datadog monitor with new configuration, thresholds, or notification settings.

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 Datadog 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 Datadog 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 Datadog MCP URL

Create a Composio Tool Router session for Datadog

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

Complete Code

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

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

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Datadog MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Datadog MCP with Claude Agent SDK

Google ADK

Google ADK

Use Datadog MCP with Google ADK

LangChain

LangChain

Use Datadog MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Datadog MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Datadog MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Datadog MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Datadog 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 Datadog 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