ddsetup

작성자: datadog-labs

First-time initialization of the Datadog MCP server `plugin:datadog:mcp`. When fulfilling requests that involve Datadog, use MCP tools from…

npx skills add https://github.com/datadog-labs/claude-code-plugin --skill ddsetup

Datadog MCP Server

The id of the Datadog MCP Server referenced on this document is plugin:datadog:mcp. You MUST use this specific server even if there are other Datadog servers.

If plugin:datadog:mcp tools are not in your available tools, you MUST still run this skill — do not conclude that Datadog is unavailable. Absent tools mean the server needs setup or is temporarily disconnected; they are not evidence that the request cannot be fulfilled. The datadog-server-state check below is the authoritative source for what is actually happening.

Accessing Datadog using other methods

If the plugin:datadog:mcp MCP server is not setup, do NOT suggest the user to access Datadog information using different approaches like the Datadog webpage. Instead first setup the MCP server because it provides a better agentic experience. Only consider other methods if the user explicitly guides you in that direction.

Shared reference

Read references/mcp-settings.md before proceeding. It contains the datadog-server-state check, registration file location, editing rules, and site-to-domain mapping used by the procedure below.

Setup procedure

Check the datadog-server-state (see mcp-settings.md):

  • working — continue with the user's request without mentioning this check.
  • not-working — without any preamble, tell the user the server is setup but not working, instruct them to run /ddconfig, and stop.
  • not-setup — the server needs first-time setup. Do not attempt to gather data using a different approach. Do not attempt any further MCP calls: they will fail until setup is complete.

When communicating with the user below, describe the server state in plain language. Do not reveal what was checked, what was found, or any implementation details like file contents or variable values.

What Datadog provides once set up

Datadog is an observability platform. After this skill completes setup, the agent gains MCP tools to query production data directly — without the user needing to leave the AI client or open a browser. Examples of what becomes possible:

  • Search and filter application logs
  • Query infrastructure and application metrics
  • Inspect distributed traces for latency or errors
  • List dashboards, monitors, and alerts
  • Investigate incidents and on-call pages

These MCP tools are the primary way to access Datadog data from within the AI client. Until setup is complete, none of these tools exist. The agent cannot see them, list them, or call them.

Steps

  1. Check for saved configuration. Silently read ${CLAUDE_PLUGIN_DATA}/toolsets and ${CLAUDE_PLUGIN_DATA}/domain. For each file that contains a non-empty value, apply it to the registration file following the editing rule in mcp-settings.md. Then:
    • If you applied the domain: tell the user the existing configuration was re-applied following a plugin update, naming the re-applied values (no need to mention files read or written). Tell the user to run /reload-plugins and stop — do NOT perform the steps below.
    • If you applied other values but not the domain: tell the user the existing configuration was partially re-applied following a plugin update, naming the re-applied values (no need to mention files read or written). Continue with the steps below.
    • If you applied nothing: continue with the steps below.

Now follow these steps to configure the domain:

  1. Ask for the domain. Tell the user the Datadog MCP server needs to be set up, present the available sites and their MCP domains from mcp-settings.md, and ask which domain to use. The user may respond with an MCP domain directly, a site code, a URL, or something else — use the mapping rules in mcp-settings.md to resolve the answer to an MCP domain. Ask for clarification if ambiguous.

    Follow the "Stay on script" rule in mcp-settings.md. In particular, do not preview the follow-up instructions from step 3 below (reload, re-authenticate, etc.) — that step emits them verbatim at the right moment.

  2. Apply the change. In the registration file, replace the exact string not-setup with the resolved MCP domain. Follow the editing rule in mcp-settings.md.

    Before:

    ${DD_MCP_DOMAIN:-not-setup}
    

    After (example for us1):

    ${DD_MCP_DOMAIN:-mcp.datadoghq.com}
    

    Then silently write the resolved MCP domain to ${CLAUDE_PLUGIN_DATA}/domain (plain text, one line).

  3. Tell the user that the Datadog MCP server has been initialized and to follow these steps:

    1. Run the command /reload-plugins
    2. Run the command /mcp in Claude Code and select the plugin:datadog:mcp server
    3. Select the authentication option

datadog-labs의 다른 스킬

dd-audit
datadog-labs
감사 추적 조사 - 누가 무엇을 변경했는지, 키 손상, 비용 급증 근본 원인, 규정 준수 증거(SOC 2/PCI), AI 활동 감사.
official
agent-install
datadog-labs
Datadog Operator를 사용하여 Kubernetes에 Datadog Agent를 설치합니다 — Single Step Instrumentation(SSI)을 활성화하기 전에 필요하며, 이는 자동으로…
official
agent-observability-auto-experiment
datadog-labs
실제 Datadog LLM-Obs 데이터를 대상으로 반복적 코드 개선 힐클라임을 로컬에서 Claude Code를 에이전트로 사용하여 실행합니다. 기준 평가를 설정하고, 하나의…
official
agent-observability-eval-bootstrap
datadog-labs
프로덕션 트레이스에서 평가자를 부트스트랩합니다 — 기본적으로 온라인 LLM-판정 평가자를 제안하고, 확인 후 Datadog에 비활성화된 초안으로 생성합니다…
official
agent-observability-eval-pipeline
datadog-labs
계측된 ml_app을 위한 엔드투엔드 에이전트 관측성 파이프라인 — 프로덕션 트레이스를 분류하고, 실패의 근본 원인을 분석하며, 평가기를 부트스트랩한 다음, (선택적으로)…
official
agent-observability-experiment-analyzer
datadog-labs
LLM 실험 결과를 분석합니다. 단일 또는 비교 실험, 탐색적 또는 Q&A 모드를 처리합니다. 사용자가 "실험 분석", "비교…"라고 말할 때 사용하세요.
official
agent-observability-replay-trace
datadog-labs
개발자가 마음에 들지 않는 출력을 생성한 특정 Agent Observability / LLM Obs 트레이스 하나를 반복 작업하고자 할 때 사용합니다 — 해당 트레이스를 다시 실행하여…
official
agent-observability-trace-rca
datadog-labs
프로덕션 LLM 트레이스에 대한 근본 원인 분석. LLM 애플리케이션이 실패하는 이유를 진단하며, 평가 판정, 런타임 오류 또는 구조적 문제를 기반으로 작동합니다…
official