Skip to main content
Datadog is a comprehensive monitoring and analytics platform for cloud-scale infrastructure, applications, and logs. The Datadog MCP server lets you monitor infrastructure, query metrics, search logs, manage incidents, and control monitors using natural language.

​
What Can It Do?

  • Monitor management including create, update, mute, and delete monitors
  • Query metrics with timeseries data and aggregation
  • Search logs with advanced filtering and time ranges
  • Incident management for tracking and coordinating responses
  • Dashboard operations including create, update, and view dashboards
  • Host management including muting and listing infrastructure hosts
  • SLO tracking for service level objectives
  • Synthetic monitoring for proactive testing

​
Where to Use It

Add Datadog as a tool to any agent. The agent can then monitor your infrastructure conversationally, choosing the right actions based on context. To add an MCP tool to your agent:
  1. Open your agent’s configuration
  2. Click Add tools → Connect an app with MCP
  3. Search for the integration and select it
  4. Enter your Datadog API credentials
You can control which tools your agent has access to. After adding an integration, click on it to enable or disable specific tools based on what your agent needs.

​
In Workflows (Via Agent Node)

For automated pipelines, use an Agent Node with Datadog tools. This gives you the flexibility of an agent within a deterministic workflow.

​
As a Custom MCP Node

You can also create a standalone MCP node for a specific action. This generates a reusable node that performs one task, useful when you need the same operation repeatedly in workflows.
To create a custom MCP node:
  1. Go to your node library and search for the integration
  2. Click Create a node with AI
  3. Describe the specific action you want (e.g., “List all monitors in alert state”)
  4. Test the node and save it for reuse
Custom MCP nodes are single-purpose by design. For tasks that require multiple steps or dynamic decision-making, use an agent instead.

​
Authentication

Datadog uses API key authentication. When connecting your Datadog account, you’ll need to provide:
  • API Key: Your Datadog API key for authentication
  • Application Key: Your Datadog Application key for authorization
  • Site: Your Datadog site (e.g., datadoghq.com, datadoghq.eu, us3.datadoghq.com)
To create API and Application keys:
  1. Log in to your Datadog account
  2. Navigate to Organization Settings → API Keys to create an API key
  3. Navigate to Organization Settings → Application Keys to create an Application key
  4. Copy both keys and your site URL for use in Gumloop
Keep your API and Application keys secure. These keys provide access to your Datadog account and should not be shared publicly.

​
Available Tools

​
Monitor Tools

​
Metrics Tools

​
Logs Tools

​
Incident Tools

​
Dashboard Tools

​
Host Tools

​
Event Tools

​
Downtime Tools

​
SLO Tools

​
Synthetics Tools

​
Example Prompts

Use these with your agent or in the Agent Node: List alerting monitors:
Query metrics:
Search logs:
Create an incident:
Mute a monitor:
Check SLO status:

​
Troubleshooting

Agents are smart enough to chain multiple API calls together. For example, asking “Mute all monitors for the web service during maintenance” will list the monitors first, then mute each one. If results seem off, check the agent’s step-by-step reasoning.

​
Need Help?

Use this integration directly in Claude or Cursor. Connect remotely via the Datadog MCP server using credentials from your Connectors page.