Datadog MCP Server
Community MCP server for interacting with Datadog APIs including incidents, metrics, logs, monitors, dashboards, traces, hosts, downtimes, and RUM.
Score Breakdown
Server Info
- Package
- @winor30/mcp-server-datadog
- Registry
- npm
- Repository
- winor30/mcp-server-datadog
- Maintainer
- Community
- Category
- Developer Tools
- Tags
- monitoringmetricslogs
- Last Scanned
- 7 Apr 2026
Findings
5 issuesAuthentication & Identity
HIGHNo per-request auth - requires instance-per-user
Stdio-only transport. Requires DATADOG_API_KEY and DATADOG_APP_KEY env vars (both mandatory, validated at startup). DATADOG_SITE and DATADOG_SUBDOMAIN are optional. Shared credentials with full API+APP key access. For multi-tenant deployment, the platform must spawn a separate server instance per user.
Add HTTP/SSE transport to accept per-request Authorization headers, or implement the MCP OAuth spec.
Tool Schema Quality
MEDIUMOnly 5 of 21 schemas have parameter constraints
Most schemas lack maxLength, enum, or pattern constraints on string parameters.
Add constraints to string parameters, especially on write operations.
Data Exposure
MEDIUM4 list operations lack pagination
list_incidents has pageSize/pageOffset pagination. get_logs and list_traces have limit params. list_hosts has start/count pagination. However, list_dashboards, get_monitors, list_downtimes, and get_rum_applications return all results without pagination. Full records are always returned.
Add limit/offset or cursor-based pagination.
LOWNo field selection on responses
Responses return full records rather than projected fields.
Implement field selection to return only relevant fields.
Maintenance & Trust
LOWCommunity-maintained by winor30
No official vendor backing.
Seek vendor verification.
Tools
21 total| Name | Description | Risk |
|---|---|---|
| list_incidents | Get incidents from Datadog | read |
| get_incident | Get an incident from Datadog | read |
| query_metrics | Query timeseries points of metrics from Datadog | read |
| get_logs | Search and retrieve logs from Datadog | read |
| get_all_services | Extract all unique service names from logs | read |
| get_monitors | Get monitors status from Datadog | read |
| list_dashboards | Get list of dashboards from Datadog | read |
| get_dashboard | Get a dashboard from Datadog | read |
| list_traces | Get APM traces from Datadog | read |
| mute_host | Mute a host in Datadog | write |
| unmute_host | Unmute a host in Datadog | write |
| list_hosts | Get list of hosts from Datadog | read |
| get_active_hosts_count | Get the total number of active hosts in Datadog (defaults to last 5 minutes) | read |
| list_downtimes | List scheduled downtimes from Datadog | read |
| schedule_downtime | Schedule a downtime in Datadog | write |
| cancel_downtime | Cancel a scheduled downtime in Datadog | write |
| get_rum_applications | Get all RUM applications in the organization | read |
| get_rum_events | Search and retrieve RUM events from Datadog | read |
| get_rum_grouped_event_count | Search, group and count RUM events by a specified dimension | read |
| get_rum_page_performance | Get page (view) performance metrics from RUM data | read |
| get_rum_page_waterfall | Retrieve RUM page (view) waterfall data filtered by application name and session ID | read |
Deploy Datadog MCP Server securely
CompleteFlow adds per-user authentication, permission scoping, and audit logging to any MCP server out of the box.
Deploy on CompleteFlow