Datadog MCP Server

Datadog MCP server - 165 tools for metrics, monitors, logs, APM, RUM, incidents, CI/CD, status pages, fleet automation, and more

Local serverstdioTypeScript

What is the Datadog MCP server?

Connect Datadog to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Datadog MCP server - 165 tools for metrics, monitors, logs, APM, RUM, incidents, CI/CD, status pages, fleet automation, and more. The datadog mcp server is what makes that connection.

What the server does

Connect the server to Claude Desktop or Claude Code, then paste any of these:

  • Aggregation tools — — analyze-monitor-state and slo-compliance-snapshot collapse 5–7 sequential API calls into one structured response with a caveats array for partial failures. No other Datadog MCP ships this pattern
  • Full SLO CRUD — — create, update, delete SLOs (and their corrections). The official Bits AI MCP and community alternatives are read-only on SLOs
  • Fleet Automation — — 15 tools across deployments and schedules. Only this server
  • Status Pages — — 21 tools for full status-page lifecycle (components, degradations, maintenances). Only this server
  • Token-efficient by design — — extractFields projection, DD_TOOLS/DD_DISABLE 16-category toggles, and a search-tools meta-tool keep LLM context low across 163 tools
  • Apps SDK card — — slo-compliance-snapshot renders as a visual card on ChatGPT clients via _meta["openai/outputTemplate"]. Claude clients receive the same JSON content (non-breaking)

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Token — efficient by design** — extractFields projection, DD_TOOLS/DD_DISABLE 16-category toggles, and a search-tools meta-tool keep LLM context low across
  • triage-incident — given an incident ID, walks linked monitors, recent error spikes, and recent deploys
  • audit-monitor-noise — flag flapping monitors via alert frequency × MTTR
  • analyze-rum-error-spike — diff RUM error rates across two windows, attribute to top error groups
  • investigate-slow-trace — given a slow trace ID, traverse the span tree and surface bottleneck spans
  • extractFields — token-efficient response projections
  • createWrapToolHandler — domain-specific redaction (DD_API_KEY/DD_APP_KEY) + Datadog ApiException error extraction
  • search — tools meta-tool
  • Deployment — Remote (managed by Datadog)
  • Auth — Datadog SSO
  • Sites — Public Datadog sites
  • Variable — Required

Installation

@us-all/datadog-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Credentials and setup notes

Configuration is passed through the environment: DD_API_KEY, DD_APP_KEY, DD_SITE, MCP_HTTP_TOKEN, MCP_HTTP_HOST. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Datadog's toolset — Token, triage-incident, audit-monitor-noise and 11 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Datadog.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Tokenefficient by design** — extractFields projection, DD_TOOLS/DD_DISABLE 16-category toggles, and a search-tools meta-tool keep LLM context low across 163 tools.
triage-incidentgiven an incident ID, walks linked monitors, recent error spikes, and recent deploys.
audit-monitor-noiseflag flapping monitors via alert frequency × MTTR.
analyze-rum-error-spikediff RUM error rates across two windows, attribute to top error groups.
investigate-slow-tracegiven a slow trace ID, traverse the span tree and surface bottleneck spans.
extractFieldstoken-efficient response projections
createWrapToolHandlerdomain-specific redaction (DD_API_KEY/DD_APP_KEY) + Datadog ApiException error extraction
searchtools meta-tool
DeploymentRemote (managed by Datadog)
AuthDatadog SSO
SitesPublic Datadog sites
VariableRequired
DD_API_KEY
DD_APP_KEY

How to install the Datadog MCP server

{
  "mcpServers": {
    "datadog": {
      "command": "npx",
      "args": ["-y", "@us-all/datadog-mcp"],
      "env": {
        "DD_API_KEY": "<your-api-key>",
        "DD_APP_KEY": "<your-app-key>",
        "DD_SITE": "datadoghq.com"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
DD_API_KEYCredential the server authenticates with.Yes
DD_APP_KEYCredential the server authenticates with.Yes
DD_SITEConfiguration value read at startup.Optional
MCP_HTTP_TOKENCredential the server authenticates with.Yes
MCP_HTTP_HOSTEndpoint or connection string the server talks to.Optional

Example prompts to try

  • Use Datadog to Token.
  • Use Datadog to triage-incident.
  • Use Datadog to audit-monitor-noise.

Frequently asked questions

It connects Datadog to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Token, triage-incident, audit-monitor-noise, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Datadog directly.