Automate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas.
npxskills add sickn33/antigravity-awesome-skills--skill datadog-automationLoading…
Automate Datadog monitoring and observability operations through Composio's Datadog toolkit via Rube MCP.
RUBE_MANAGE_CONNECTIONS with toolkit datadogRUBE_SEARCH_TOOLS first to get current tool schemasGet Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit datadogWhen to use: User wants to query metric data or list available metrics
Tool sequence:
DATADOG_LIST_METRICS - List available metric names [Optional]DATADOG_QUERY_METRICS - Query metric time series data [Required]Key parameters:
query: Datadog metric query string (e.g., avg:system.cpu.user{host:web01})from: Start timestamp (Unix epoch seconds)to: End timestamp (Unix epoch seconds)q: Search string for listing metricsPitfalls:
aggregation:metric_name{tag_filters}from and to are Unix epoch timestamps in seconds, not millisecondsavg, sum, min, max, count{host:web01,env:prod}When to use: User wants to search log entries or list log indexes
Tool sequence:
DATADOG_LIST_LOG_INDEXES - List available log indexes [Optional]DATADOG_SEARCH_LOGS - Search logs with query and filters [Required]Key parameters:
query: Log search query using Datadog log query syntaxfrom: Start time (ISO 8601 or Unix timestamp)to: End time (ISO 8601 or Unix timestamp)sort: Sort order ('asc' or 'desc')limit: Number of log entries to returnPitfalls:
service:web status:errorWhen to use: User wants to create, update, mute, or inspect monitors
Tool sequence:
DATADOG_LIST_MONITORS - List all monitors with filters [Required]DATADOG_GET_MONITOR - Get specific monitor details [Optional]DATADOG_CREATE_MONITOR - Create a new monitor [Optional]DATADOG_UPDATE_MONITOR - Update monitor configuration [Optional]DATADOG_MUTE_MONITOR - Silence a monitor temporarily [Optional]DATADOG_UNMUTE_MONITOR - Re-enable a muted monitor [Optional]Key parameters:
monitor_id: Numeric monitor IDname: Monitor display nametype: Monitor type ('metric alert', 'service check', 'log alert', 'query alert', etc.)query: Monitor query defining the alert conditionmessage: Notification message with @mentionstags: Array of tag stringsthresholds: Alert threshold values (critical, warning, ok)Pitfalls:
type must match the query type; mismatches cause creation failuresmessage supports @mentions for notifications (e.g., @slack-channel, @pagerduty)critical at minimumWhen to use: User wants to list, view, update, or delete dashboards
Tool sequence:
DATADOG_LIST_DASHBOARDS - List all dashboards [Required]DATADOG_GET_DASHBOARD - Get full dashboard definition [Optional]DATADOG_UPDATE_DASHBOARD - Update dashboard layout or widgets [Optional]DATADOG_DELETE_DASHBOARD - Remove a dashboard (irreversible) [Optional]Key parameters:
dashboard_id: Dashboard identifier stringtitle: Dashboard titlelayout_type: 'ordered' (grid) or 'free' (freeform positioning)widgets: Array of widget definition objectsdescription: Dashboard descriptionPitfalls:
layout_type cannot be changed after creation; must recreate the dashboardWhen to use: User wants to post events or schedule maintenance downtimes
Tool sequence:
DATADOG_LIST_EVENTS - List existing events [Optional]DATADOG_CREATE_EVENT - Post a new event [Required]DATADOG_CREATE_DOWNTIME - Schedule a maintenance downtime [Optional]Key parameters for events:
title: Event titletext: Event body text (supports markdown)alert_type: Event severity ('error', 'warning', 'info', 'success')tags: Array of tag stringsKey parameters for downtimes:
scope: Tag scope for the downtime (e.g., host:web01)start: Start time (Unix epoch)end: End time (Unix epoch; omit for indefinite)message: Downtime descriptionmonitor_id: Specific monitor to downtime (optional, omit for scope-based)Pitfalls:
text supports Datadog's markdown format including @mentionshost:web01, env:stagingend creates an indefinite downtime; always set an end time for maintenancemonitor_id narrows to a single monitor; scope applies to all matching monitorsWhen to use: User wants to list infrastructure hosts or inspect distributed traces
Tool sequence:
DATADOG_LIST_HOSTS - List all reporting hosts [Required]DATADOG_GET_TRACE_BY_ID - Get a specific distributed trace [Optional]Key parameters:
filter: Host search filter stringsort_field: Sort hosts by field (e.g., 'name', 'apps', 'cpu')sort_dir: Sort direction ('asc' or 'desc')trace_id: Distributed trace ID for trace lookupPitfalls:
Metric alerts:
avg(last_5m):avg:system.cpu.user{env:prod} > 90
Log alerts:
logs("service:web status:error").index("main").rollup("count").last("5m") > 10
key:value format: host:web01, env:prod, service:api{host:web01,env:prod} (AND logic)host:web*page and page_size or offset-based pagination depending on endpointTimestamps:
Query Syntax:
aggregation:metric{tags}field:value pairsRate Limits:
| Task | Tool Slug | Key Params |
|---|---|---|
| Query metrics | DATADOG_QUERY_METRICS | query, from, to |
| List metrics | DATADOG_LIST_METRICS | q |
| Search logs | DATADOG_SEARCH_LOGS | query, from, to, limit |
| List log indexes | DATADOG_LIST_LOG_INDEXES | (none) |
| List monitors | DATADOG_LIST_MONITORS | tags |
| Get monitor | DATADOG_GET_MONITOR | monitor_id |
| Create monitor | DATADOG_CREATE_MONITOR | name, type, query, message |
| Update monitor | DATADOG_UPDATE_MONITOR | monitor_id |
| Mute monitor | DATADOG_MUTE_MONITOR | monitor_id |
| Unmute monitor | DATADOG_UNMUTE_MONITOR | monitor_id |
| List dashboards | DATADOG_LIST_DASHBOARDS | (none) |
| Get dashboard | DATADOG_GET_DASHBOARD | dashboard_id |
| Update dashboard | DATADOG_UPDATE_DASHBOARD | dashboard_id, title, widgets |
| Delete dashboard | DATADOG_DELETE_DASHBOARD | dashboard_id |
| List events | DATADOG_LIST_EVENTS | start, end |
| Create event | DATADOG_CREATE_EVENT | title, text, alert_type |
| Create downtime | DATADOG_CREATE_DOWNTIME | scope, start, end |
| List hosts | DATADOG_LIST_HOSTS | filter, sort_field |
| Get trace | DATADOG_GET_TRACE_BY_ID | trace_id |
This skill is applicable to execute the workflow or actions described in the overview.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).