agentleFS
datadog-labsdatadog-labs/claude-code-plugin/skills/ddconfig/SKILL.md

ddconfig

Skill18 starsChanged 6 months agoApache-2.0View on GitHub

Configures or troubleshoots the plugin's Datadog MCP server. Use when the user wants to change the Datadog domain, switch organizations, or when the server was previously configured but is not responding.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When communicating with the user below, describe the server state and actions in plain language.

    line 24
  2. Very specific:

    Run the command /mcp in Claude Code and select the plugin:datadog:mcp server

    line 33
  3. Distinctive:

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

    line 38
  4. Very specific:

    Follow the "Stay on script" rule in mcp-settings.md.

    line 48
  5. Distinctive:

    After (switching to us1):

    line 58
  6. Very specific:

    Run the command /reload-plugins

    line 67
  7. Distinctive:

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

    line 76
  8. Distinctive:

    If on the same domain:

    line 78
  9. Distinctive:

    If on a different domain:

    line 84
  10. Distinctive:

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

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

This is a hard gate, not a suggestion. You MUST actually read references/mcp-settings.md before proceeding and writing any user-facing text, asking any question, or performing any file edit suggested by this skill — even if you believe you already know its contents from a prior turn or a prior session. Do not answer from memory of Datadog site codes, domains, or file paths; the tables and path rules in that file are the only authoritative source, and they can differ from your general knowledge or from what you've seen in other contexts.

The references/mcp-settings.md file 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's 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 whoami → dd_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}

    Verify the edit before reporting success. Re-read the registration file at the exact path you derived and confirm the new MCP domain is present and the previous one is gone. Do not tell the user the domain has been changed until this re-read confirms it. If the file still holds the old domain, the edit landed somewhere else — re-derive the path using the rule in mcp-settings.md and apply the change again rather than reporting success.

  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 "Clear authentication" option, then run /mcp again and select the plugin:datadog:mcp server
    4. 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 "Clear authentication" option, then run /mcp again and select the plugin:datadog:mcp server
      3. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.