No install? Use cloud.anythingmcp.com directly.
Sign in, install the Datadog in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Datadog klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Datadog
Query Datadog (metrics, logs, monitors, events, incidents, dashboards) from any AI agent. 8 tools, dual-key auth.
Einrichtung
This connector wraps the Datadog REST API v1/v2 (api.datadoghq.com).
Setup:
- In your Datadog org → Personal Settings → Organization Settings → API Keys → create or copy an API key. Set
DATADOG_API_KEY. - Organization Settings → Application Keys → create an application key with at least
monitors_read,logs_read_data,dashboards_read,events_readscopes. SetDATADOG_APP_KEY. - Site matters: Datadog has multiple regions: US1 (datadoghq.com — default), US3 (us3.datadoghq.com), US5 (us5.datadoghq.com), EU1 (datadoghq.eu), AP1 (ap1.datadoghq.com), US1-FED (ddog-gov.com). If your org is on a non-US1 site, change
baseUrlaccordingly. …
Voraussetzungen: DATADOG_API_KEY, DATADOG_APP_KEY
Connector lokal installieren
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Öffne http://localhost:3000/connectors/store, wähle Datadog und trage die unter Voraussetzungen aufgelisteten Variablen ein.
Verfügbare Tools
| Tool | What it does |
|---|---|
datadog_query_metrics | Run a metrics query over a time window |
datadog_search_logs | Search logs using the Logs Search syntax |
datadog_list_monitors | List monitors |
datadog_get_monitor | Get a single monitor by ID with full definition (query, thresholds, notifications, state) |
datadog_list_dashboards | List all dashboards in the org |
datadog_get_dashboard | Fetch a dashboard's full layout: widgets, queries, template variables |
datadog_list_events | List events in a time range |
datadog_post_event | Post an event to the Datadog event stream (useful for marking deploys, releases, manual incidents) |