How to Use the Datadog AI (LLM Observability) MCP in CrewAI

Q: Can I have one CrewAI agent watch for Datadog AI (LLM Observability) incidents and another one investigate them?

Yes, that's the ideal way to use CrewAI. Give the listincidents tool to a "Watcher" agent and the searchllmspans tool to an "Investigator" agent. This MCP server makes that collaboration possible by letting them share information.

Q: Can my agents manage service accounts in Datadog?

They can list them. The listserviceaccounts tool allows an agent to get a list of accounts, which is the first step in many audit or reporting tasks. For example, an agent could iterate through the list to check token usage for each one.

Deploy autonomous agent crews to manage your Datadog AI (LLM Observability) stack. Monitor, analyze, and respond without human intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datadog AI (LLM Observability) MCP to CrewAI

Create your Vinkius account to connect Datadog AI (LLM Observability) 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 AI (LLM Observability) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Dedicated Monitoring Crew

This is what CrewAI was built for. Assign a "Monitor Agent" the `list_incidents` and `list_events` tools. Its only job is to constantly poll Datadog for new problems. When the Monitor Agent finds something, it passes the incident ID to an "Analyst Agent." This second agent uses `search_llm_spans` to investigate the root cause, then hands a summary to a "Responder Agent" which might use `create_event` to post an update.

Autonomous Metric Analysis

Set up an agent whose role is to watch costs. It uses the `query_metrics` tool to track `datadog.llm_observability.tokens` across different models or services. If it detects a spike, it can trigger another agent in the crew to investigate. That agent could use `list_service_accounts` and `search_llm_spans` to pinpoint which user or process is responsible for the increased token consumption. This is how you build a self-governing observability system.

Autonomous Housekeeping with CrewAI

You can build a crew for maintenance. One agent periodically runs `list_ai_monitors` to get a list of all active monitors. A second "Auditor Agent" checks this list against a master configuration file. If the Auditor finds a monitor that's missing or configured incorrectly, it tasks a "Fixer Agent" with using `create_monitor` to fix the drift. This MCP Server provides all the necessary tools for your crew to run autonomously and keep your Datadog setup clean.

Setup guide

Set up Datadog AI (LLM Observability) 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 AI (LLM Observability) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Datadog AI (LLM Observability) 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 AI (LLM Observability) 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 AI (LLM Observability) MCP in CrewAI

Yes, that's the ideal way to use CrewAI. Give the `list_incidents` tool to a "Watcher" agent and the `search_llm_spans` tool to an "Investigator" agent. This MCP server makes that collaboration possible by letting them share information.

You could have a "Provisioning" agent responsible for setup. When a new service is deployed, another agent tasks the Provisioning agent to call `create_monitor` and `list_dashboards` to ensure the new service has the right observability from day one.

A great starter crew has three agents. A "Metric-Watcher" agent uses `query_metrics`. An "Incident-Watcher" uses `list_incidents`. A "Reporter" agent takes input from both and uses `create_event` to post consolidated updates to a Datadog event stream.

They can list them. The `list_service_accounts` tool allows an agent to get a list of accounts, which is the first step in many audit or reporting tasks. For example, an agent could iterate through the list to check token usage for each one.

The server only touches observability data from your Datadog account—things like LLM span details, metric values for token usage, and incident metadata. Your Datadog credentials are encrypted and stored by Vinkius, not your CrewAI code. The agents operate in a zero-trust environment using ephemeral tokens provided by the MCP server.

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