Datadog MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATADOG_SITE | No | The Datadog site (e.g. datadoghq.eu) | |
| DATADOG_API_KEY | Yes | Your Datadog API key | |
| DATADOG_APP_KEY | Yes | Your Datadog Application key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_incidentsC | Get incidents from Datadog |
| get_incidentC | Get an incident from Datadog |
| query_metricsC | Query timeseries points of metrics from Datadog |
| list_metricsC | List active metric names from Datadog |
| get_monitorsC | Get monitors status from Datadog |
| list_dashboardsC | Get list of dashboards from Datadog |
| get_dashboardC | Get a dashboard from Datadog |
| list_spansC | Get a list of spans matching a search query |
| get_rum_applicationsB | Get all RUM applications in the organization |
| get_rum_eventsC | Search and retrieve RUM events from Datadog |
| get_rum_grouped_event_countC | Search, group and count RUM events by a specified dimension |
| get_rum_page_performanceC | Get page (view) performance metrics from RUM data |
| get_rum_page_waterfallB | Retrieve RUM page (view) waterfall data filtered by application name and session ID |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Most tools have distinct purposes targeting specific Datadog resources like dashboards, incidents, monitors, RUM, metrics, and spans. However, there is some potential overlap between 'get_rum_events' and 'get_rum_grouped_event_count' as both involve retrieving RUM events, though the latter adds grouping and counting functionality. Overall, the descriptions help clarify differences, but a few tools could be slightly confusing without careful reading.
The naming is highly consistent, following a clear verb_noun pattern throughout. All tools use either 'get_' or 'list_' prefixes followed by a specific resource name, with no deviations in style or convention. This predictability makes it easy for agents to understand and select tools based on their intended actions.
With 13 tools, the count is well-scoped for a Datadog monitoring and observability server. It covers key areas like dashboards, incidents, monitors, RUM, metrics, and spans without being overwhelming. Each tool appears to serve a distinct purpose, contributing to a comprehensive toolset that aligns with the server's domain.
The toolset provides strong read-only coverage for Datadog's core features, including retrieval and listing of dashboards, incidents, monitors, RUM data, metrics, and spans. However, there are notable gaps in write operations (e.g., no create, update, or delete tools) and limited query capabilities beyond basic metrics and RUM events. Agents can work around this for read-heavy tasks, but full lifecycle management is not supported.