Can I use Datadog as a CLI?

Yes. KosmoKrator exposes a Datadog CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Datadog through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Datadog tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Datadog credentials stored?

Datadog credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Datadog MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

analytics

Datadog MCP, CLI, and Lua Integration for AI Agents

Datadog integration docs for AI agents: MCP gateway setup, Datadog CLI commands, Lua API reference, credentials, and function schemas.

Datadog for agents

Credentials can be configured manually in web or CLI hosts.

Use this integration from Lua code mode, the headless integrations CLI, or the KosmoKrator MCP gateway. The same package metadata powers all three surfaces.

Agent Surfaces

Datadog CLIHeadless setup, JSON output, direct function calls. Datadog MCPExpose selected tools to local MCP clients. Datadog LuaAgent-facing namespace and Lua reference. FeedbackReport missing tools, auth issues, or bad metadata.

Machine-Readable Metadata

integration_slug: datadog
route_slug: datadog
package: datadog
auth_strategy: api_key
cli_setup_supported: true
cli_runtime_supported: true
mcp_gateway_supported: true
lua_supported: true

Function Catalog

Function	Type	Parameters	Description
`datadog.datadog_list_monitors`	Read `read`	4	List Datadog monitors. Optionally filter by name or tags. Returns monitor IDs, names, types, states, and query definitions.
`datadog.datadog_get_monitor`	Read `read`	1	Get full details of a specific Datadog monitor by ID. Returns the monitor query, thresholds, message, and current state.
`datadog.datadog_create_monitor`	Write `write`	7	Create a new Datadog monitor. Specify the monitor type, query, name, and optional message and thresholds. Common types: "metric alert", "service check", "event alert".
`datadog.datadog_update_monitor`	Write `write`	8	Update an existing Datadog monitor. Provide the monitor ID and the fields to update (name, query, message, options, tags, etc.).
`datadog.datadog_delete_monitor`	Write `write`	1	Delete a Datadog monitor by ID. This action is permanent and cannot be undone.
`datadog.datadog_query_metrics`	Read `read`	3	Query Datadog metrics between two timestamps. Use Datadog query syntax (e.g., "avg:system.cpu.user{env:production} by {host}"). Returns time series data points.
`datadog.datadog_list_dashboards`	Read `read`	0	List all Datadog dashboards. Returns dashboard IDs, titles, descriptions, and modification dates.
`datadog.datadog_get_dashboard`	Read `read`	1	Get full details of a specific Datadog dashboard by ID. Returns the dashboard layout, widgets, and template variables.
`datadog.datadog_post_event`	Write `write`	9	Post an event to the Datadog event stream. Specify title, text, priority, tags, and alert type. Events appear in the event timeline.
`datadog.datadog_get_current_user`	Read `read`	0	Get the currently authenticated Datadog user. Useful for verifying credentials and identifying the connected account.