Datadog MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DD_API_KEY | Yes | Your Datadog API key from the Datadog API Keys page | |
| DD_APP_KEY | Yes | Your Datadog application key from the Datadog API Keys page |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_logsC | Tool for searching Datadog logs |
| search_spansC | Tool for searching Datadog trace spans |
| aggregate_spansC | Tool for aggregating Datadog trace spans |
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 3 tools
The three tools are mostly distinct, with 'aggregate_spans' focusing on aggregation of trace data, 'search_logs' targeting log data, and 'search_spans' targeting trace data. However, 'aggregate_spans' and 'search_spans' both operate on spans and could be confused for overlapping purposes, though their descriptions clarify one aggregates and the other searches.
All tool names follow a consistent verb_noun pattern with snake_case, using 'aggregate' and 'search' as verbs paired with specific nouns like 'spans' and 'logs'. There are no deviations in naming style or convention.
With only 3 tools, the server feels thin for a Datadog integration, which typically involves monitoring, metrics, dashboards, and alerts. While the tools cover traces and logs, the scope is limited, making it borderline appropriate for the apparent domain.
The tool surface has significant gaps for a Datadog server, missing core operations like querying metrics, managing dashboards, setting alerts, or accessing APM data beyond spans. Agents will struggle with incomplete coverage for common monitoring workflows.