Datadog is a Monitoring MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent infrastructure monitoring and APM. Install in 1 minute with mcpizy install datadog.
Monitoring
Infrastructure monitoring and APM
Official homepagemcpizy install datadognpx -y @datadog/mcpquery_metricsQuery metrics over a time range
Inputs
querystringrequiredfromstringrequiredtostringrequiredlist_monitorsList Datadog monitors
get_monitorGet a monitor's definition and status
Inputs
idstringrequiredlist_dashboardsList dashboards
search_logsSearch logs with a query
Inputs
querystringrequiredfromstringrequiredtostringrequiredlist_eventsList recent events
Works identically across clients. Only the config file path differs.
~/.claude.json{
"mcpServers": {
"datadog": {
"command": "npx",
"args": [
"-y",
"@datadog/mcp-server"
],
"env": {
"DD_API_KEY": "...",
"DD_APP_KEY": "...",
"DD_SITE": "datadoghq.com"
}
}
}
}.cursor/mcp.json{
"mcpServers": {
"datadog": {
"command": "npx",
"args": [
"-y",
"@datadog/mcp-server"
],
"env": {
"DD_API_KEY": "...",
"DD_APP_KEY": "...",
"DD_SITE": "datadoghq.com"
}
}
}
}~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"datadog": {
"command": "npx",
"args": [
"-y",
"@datadog/mcp-server"
],
"env": {
"DD_API_KEY": "...",
"DD_APP_KEY": "...",
"DD_SITE": "datadoghq.com"
}
}
}
}Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.
“Query Datadog: avg(last_1h):avg:system.cpu.user{env:prod}”
Uses: query_metrics
“List monitors currently in ALERT state”
Uses: list_monitors
“Search logs for `status:500 service:api` in the last hour”
Uses: search_logs
Access OpenTelemetry traces and metrics via Pydantic Logfire. Debug production issues fast.
Crash reporting and real user monitoring data. Track errors, performance, and user sessions.
Real-time production context — logs, metrics, traces. SRE intelligence for incident response.
Query metrics and alerts
If Datadog doesn't fit your stack, these Monitoring MCP servers solve similar problems.
The Datadog MCP server is an Monitoring Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents infrastructure monitoring and APM. It exposes Datadog's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install datadog` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @datadog/mcp` and restarting Claude Code.
Yes. The Datadog MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Datadog account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can infrastructure monitoring and APM directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Datadog operations, inspect results, chain Datadog with other MCP servers (see our Workflow Recipes), and automate repetitive monitoring tasks without leaving your editor.