ddconfig

작성자: datadog-labs

Configures or troubleshoots the Datadog MCP server `plugin:datadog:mcp`. Use when the user wants to change the Datadog domain, switch organizations, or when…

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

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.

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 flows below.

Entry flow

Check the datadog-server-state (see mcp-settings.md). Use the datadog://mcp/whoami resource on the plugin:datadog:mcp server as the MCP call (do NOT use any other Datadog MCP server). Do not output anything until the datadog-server-state and resource content are available, and proceed based on the results:

  • datadog-server-state=working and valid content — without any preamble, immediately show the user their current connection (from whoami): user name and email, organization name, and site (the dd_site value). Then let the user choose between using a different Datadog MCP domain or site or switching to a different Datadog organization.
  • datadog-server-state=not-setup — without any preamble, tell the user the plugin is not set up and instruct them to run /ddsetup, and stop.
  • datadog-server-state=not-working or not valid content — without any preamble, tell the user the server is configured but not working and go to the Troubleshooting Flow.

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

Troubleshooting Flow

The server is configured but not responding. Read the current domain from the registration file (see mcp-settings.md for the file format and how to find the domain), then present the user with the likely causes — do not follow these sequentially, show them all and use judgment:

  • Domain issue. Compare the domain against the site-to-domain table in mcp-settings.md. Only flag it as suspicious if it looks like a typo or a clearly malformed URL (e.g. mcp.us5.datadog.com missing the hq). A domain not in the standard table is not necessarily wrong — the user may be using a valid non-standard domain.

  • Authentication. The authentication may have expired or was never completed, and the user needs to follow these steps:

    1. Run the command /mcp in Claude Code and select the plugin:datadog:mcp server
    2. Select the authentication option
  • Network or access. The user's network may be blocking the connection, or their Datadog account may not have API access, like not having the MCP Read permission.

If the domain looks wrong, suggest running the Domain Flow to correct it.

Domain Flow

Changes the Datadog MCP domain the server connects to.

  1. Show the current domain information (from whoamidd_site if available, or from the current domain in the registration file — see mcp-settings.md for the file format). Present it in plain language (e.g. "the plugin is currently connected to …") — follow the "Stay on script" rule in mcp-settings.md.

  2. Ask for the new domain. Present the available sites and their MCP domains from mcp-settings.md, and ask which domain to switch to. 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. 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 4 below (reload, re-authenticate, etc.) — that step emits them verbatim at the right moment.

  3. Edit the domain in the registration file following the editing rule in mcp-settings.md.

    Before (example):

    ${DD_MCP_DOMAIN:-mcp.datadoghq.eu}
    

    After (switching to us1):

    ${DD_MCP_DOMAIN:-mcp.datadoghq.com}
    
  4. Tell the user the domain has been changed 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

Organization Flow

Switches to a different Datadog organization. The agent cannot do this automatically — the user must select the target organization in the browser.

Ask the user if they want to use an organization on the same domain or on a different domain.

  • If on the same domain:

    • The user needs to reauthenticate and, during sign-in, choose the target organization in the browser, using the following steps:
      1. Run the command /mcp in Claude Code and select the plugin:datadog:mcp server
      2. Select the authentication option
  • If on a different domain:

    • Run the Domain Flow telling the user to choose the target organization in the browser during sign-in.

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