Datadog MCP server
Last verified: 2026-09
Metrics, logs, and monitors.
Community Cloud & infra Needs a secret Claude Desktop, Cursor, Windsurf, Claude Code
What it does
Community Datadog MCP: incidents, monitors, logs, dashboards, metrics, traces, hosts. Needs API key + APP key.
It sits in Cloud & infra: Most of these are admin APIs.
Good for
- get_monitors that are alerting.
- A short log query you already run in the UI.
- list_incidents / get_incident during an on-call.
- Keep write scopes off; two keys = the Datadog UI for those scopes.
Tools
- list_incidents / get_incident — Incidents.
- get_monitors / get_logs / query_metrics / list_traces / list_hosts — Telemetry.
- list_dashboards / get_dashboard — Dashboards.
Config (Claude Desktop / Cursor / Windsurf)
Paste the JSON below. Same mcpServers shape. Replace placeholder paths and secrets.
Windows paths look like C:\\Users\\you\\project, not /path/to.
Host-side steps →
Claude Desktop
| OS | Config file |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json
(usually C:\Users\<you>\AppData\Roaming\Claude\) |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Cursor
| Scope | macOS / Linux | Windows |
|---|---|---|
| This project | .cursor/mcp.json in the repo root | |
| This user | ~/.cursor/mcp.json |
%USERPROFILE%\.cursor\mcp.json |
Windsurf
| OS | Config file |
|---|---|
| macOS / Linux | ~/.codeium/windsurf/mcp_config.json |
| Windows | %USERPROFILE%\.codeium\windsurf\mcp_config.json |
{
"mcpServers": {
"datadog": {
"command": "npx",
"args": [
"-y",
"datadog-mcp-server"
],
"env": {
"DATADOG_API_KEY": "...",
"DATADOG_APP_KEY": "..."
}
}
}
}
Windsurf remote MCP: use serverUrl instead of url if the block below is HTTP.
One-liner: npx -y datadog-mcp-server
Secrets it wants: DATADOG_API_KEY, DATADOG_APP_KEY
How to get started
- Create an application key on a service account with read. Do not use an org admin app key.
- Ask for get_monitors or a short log query.
- Keep write scopes off.
Access risk
Logs and traces are often PII. Two keys = the same access as the Datadog UI for those scopes.
When to skip it
Skip it for Grafana/Prometheus if that is the stack, or for PagerDuty-only paging.
Instead: Grafana, Prometheus, PagerDuty.
Vs alternatives
| Server | Official? | Needs a secret? | Best for |
|---|---|---|---|
| Datadog | No | Yes | Metrics, logs, and monitors. |
| Grafana | No | Yes | Dashboards and datasources. |
| Prometheus | No | Yes | Instant queries against Prometheus. |
| PagerDuty | No | Yes | Incidents and on-call. |
More in Cloud & infra
FAQ
API key and APP key?
Yes. Create them on a service account with read. Org admin app keys are unnecessary.
Datadog or Grafana?
Match the stack you already pay for. Logs/traces in Datadog are often PII.
Datadog or PagerDuty?
Datadog is telemetry. PagerDuty is who wakes up. You may want both read-only.
Official Datadog?
Community package (winor30). Confirm before a prod app key.