Dashboards, monitors, logs, metrics, incidents, SLOs, APM traces via Datadog's official MCP
Use with AI AssistantsMCP
Connect Claude, Cursor, or any MCP-compatible client — then call tools directly
① Add This MCP Server
Paste into your AI client config — then all its tools are available instantly.
{
"mcpServers": {
"datadog-observability": {
"url": "https://mcp.aerostack.dev/s/aerostack/mcp-datadog",
"headers": {
"Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
}
}
}
}Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.
② Call a Tool
Ask your AI assistant to call a specific tool, or send raw JSON-RPC:
Natural Language Prompt
“Use the list_dashboards tool to list all datadog dashboards with title, description, author, layout type, and modification timestamps”
Using a Workspace?
Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.
Official proxy MCP — Dashboards, monitors, logs, metrics, incidents, SLOs, APM traces via Datadog's official MCP
Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-datadog
Datadog Observability is a proxy MCP server that forwards requests directly to the official Datadog MCP endpoint at https://mcp.datadoghq.com/api/unstable/mcp-server/mcp. All tools are maintained by Datadog — new tools are available immediately without any Aerostack update.
Type: Proxy (hosted by Datadog)
Auth: API Key + Application Key via DD_API_KEY and DD_APP_KEY
Regional endpoints: EU:
mcp.datadoghq.eu, US3:mcp.us3.datadoghq.com, US5:mcp.us5.datadoghq.com, AP1:mcp.ap1.datadoghq.com, GovCloud:mcp.ddog-gov.com
| Variable | Required | Description | How to Get |
|---|---|---|---|
DD_API_KEY | Yes | Datadog API Key | app.datadoghq.com → Organization Settings → API Keys → New Key |
DD_APP_KEY | Yes | Datadog Application Key | app.datadoghq.com → Organization Settings → Application Keys → New Key |
DD_API_KEY and DD_APP_KEY when prompted — stored encrypted, injected automaticallyOnce added, every AI agent in your workspace can query Datadog tools automatically.
"Show me all dashboards tagged with 'production'"
"Search logs for errors in the web service from the last hour"
"List all monitors that are currently alerting"
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-datadog \
-H 'Content-Type: application/json' \
-H 'X-Mcp-Secret-DD-API-KEY: your-api-key' \
-H 'X-Mcp-Secret-DD-APP-KEY: your-app-key' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_logs","arguments":{"query":"service:web status:error"}}}'
MIT
@aerostack
Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.
by @aerostack
Tasks, projects, sections, comments, teams, custom fields via Asana's official MCP
by @aerostack
Jira issues, sprints, Confluence pages via Atlassian's official MCP
by @aerostack
Cloudflare Workers, KV, R2, D1, Pages, DNS via Cloudflare's official MCP
by @aerostack
Files, frames, components, comments, variables via Figma's official MCP
by @aerostack
GitHub repos, PRs, issues, branches, code search via GitHub's official hosted MCP
by @aerostack
Dashboards, alerting, Loki logs, Tempo traces, Prometheus metrics via Grafana's official MCP
Yes. search_logs accepts a query string, time range, and index. Claude can reproduce a Datadog Logs search, summarize error patterns, and correlate them with monitor alerts.
list_monitors returns all monitors with their state. Claude filters for ALERT or WARN status and groups them by service tag, giving you a triage list without opening the Datadog UI.
query_metrics takes a Datadog metrics expression and time range. Claude can run multi-series queries like avg:system.cpu.user{*} by host and surface the top outliers.
get_dashboard returns full dashboard JSON including widget definitions and queries. Claude can read widget query strings to understand what each graph measures, but does not render charts.