Datadog Mcp

Name: Datadog Mcp
Author: tantiope

by tantiopecommunityv1.0.9

The Datadog MCP server provides AI assistants with full observability access to Datadog, enabling features like log search, APM trace filtering, and cross-correlation of logs, traces, and metrics.

From the registry: Full Datadog API access: monitors, logs, metrics, traces, dashboards, and observability tools

GitHub Repository

Install & configure

Prerequisites

required
Datadog API and App keys
Create an API key and Application key in your Datadog account with the appropriate scopes.
https://app.datadoghq.com/organization-settings/api-keys

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `datadog-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Datadog API and App keys** — Create an API key and Application key in your Datadog account with the appropriate scopes. (https://app.datadoghq.com/organization-settings/api-keys)

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","datadog-mcp"]
- required environment variables:
  - `DD_API_KEY`: Datadog API key (example: `<your_dd_api_key>`)
  - `DD_APP_KEY`: Datadog Application key (example: `<your_dd_app_key>`)
- optional environment variables:
  - `DD_SITE`: Datadog site (e.g. datadoghq.com, datadoghq.eu, us3.datadoghq.com) (example: `datadoghq.com`)
  - `MCP_DEFAULT_LIMIT`: General fallback limit (example: `50`)
  - `MCP_DEFAULT_LOG_LINES`: Default log lines to return (example: `200`)
  - `MCP_DEFAULT_METRIC_POINTS`: Default metric timeseries data points (example: `1000`)
  - `MCP_DEFAULT_TIME_RANGE`: Default time range in hours (example: `24`)

Note: Community-maintained; not officially affiliated with Datadog.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Community-maintained; not officially affiliated with Datadog.

Tools (19)

monitors

Manage monitors including listing, creating, updating, and deleting.

dashboards

Manage dashboards including listing, creating, updating, and deleting.

logs

Search and aggregate log data.

metrics

Query and manage metrics data.

traces

Search and aggregate trace data.

events

Manage events including listing, creating, and searching.

incidents

Manage incidents including listing, creating, and updating.

slos

Manage SLOs including listing, creating, and updating.

synthetics

Manage synthetic tests including listing, creating, and updating.

downtimes

Manage downtimes including listing, creating, and updating.

hosts

Manage infrastructure hosts including listing and muting.

rum

Manage RUM applications and data.

security

Manage security rules and findings.

notebooks

Environment variables

DD_API_KEYrequiredAPI key for Datadog access.

DD_APP_KEYrequiredApplication key for Datadog access.

Packages

datadog-mcp

npmv1.0.9transport: stdio

Details

Language: TypeScript
License: Apache-2.0
Released: Dec 18, 2025
Last commit: Jun 22, 2026
Registry name: io.github.TANTIOPE/datadog-mcp

Related Servers

Netdata

Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.

79.8k

Codebase Memory Mcp

Persistent codebase knowledge graph. Survives session restarts and context compaction.

35.4k

Oh My Posh Validator

Validate oh-my-posh configurations and segment snippets against the official schema.

23.2k