How to Use the Datadog MCP in CrewAI

Q: Can I restrict which Datadog tools a CrewAI agent can use?

Yes, you can use the MCPServerHTTP class from CrewAI to apply a tool filter. This prevents agents from calling destructive tools like mutemonitor while still allowing them to run listhosts.

Q: How do I connect a CrewAI agent to this Datadog MCP Server?

Simply pass the Vinkius server URL into your agent's mcps parameter during initialization. The crew automatically discovers and binds all 16 Datadog tools via MCP.

Deploy specialized CrewAI agent teams to monitor Datadog metrics, investigate logs, and resolve incidents autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datadog MCP to CrewAI

Create your Vinkius account to connect Datadog 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 Datadog with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run autonomous Datadog triage with CrewAI

Triage isn't a one-agent job, so you can set up a research agent to call `get_incident` while an analyst agent runs `search_logs` to find the exact trace that caused the failure. They share context in memory, allowing them to collaborate on a root-cause report without you having to manually coordinate their tool calls or copy-paste logs.

Let CrewAI agents post Datadog events

Keep your team informed by letting your crew document its own actions with `create_event` over the MCP Server to log a deployment status or a manual scaling action directly into Datadog. By pairing this with `check_datadog_status`, your crew ensures the monitoring pipeline is fully functional before executing any critical operations on your cluster.

Audit your Datadog setup using CrewAI teams

You can deploy a CrewAI auditor team that uses our MCP Server to call `list_monitors` and `list_slos` to identify alerts that lack proper thresholds. The crew analyzes the active alerts, flags noisy monitors, and prepares a cleanup plan that you can approve with a single command.

Setup guide

Set up Datadog 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 Datadog tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Datadog 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="Datadog Analyst",
        goal="Access and analyze Datadog data via MCP.",
        backstory="Expert analyst with direct Datadog access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Datadog 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 Datadog. 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 Datadog 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 Datadog MCP in CrewAI

CrewAI uses shared memory to pass tool outputs between agents. When one agent calls `get_incident`, the resulting JSON is immediately available to the analyst agent running `search_logs`.

Yes, you can use the `MCPServerHTTP` class from CrewAI to apply a tool filter. This prevents agents from calling destructive tools like `mute_monitor` while still allowing them to run `list_hosts`.

Simply pass the Vinkius server URL into your agent's `mcps` parameter during initialization. The crew automatically discovers and binds all 16 Datadog tools via MCP.

Yes, you can configure your crew to run hierarchically or sequentially. For example, a monitoring agent first calls `list_incidents`, then passes the active issues to an escalation agent.

No, neither CrewAI nor Vinkius stores your raw log files or infrastructure metrics. The MCP Server retrieves your telemetry data on-demand inside ephemeral, zero-trust sandboxes, discarding the payload immediately after the tool execution completes.

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