Dome Systems
Dashboard
DocsLearnHands-on LabsTemplatesHelpChangelogCLIAPIMCPSDKs

Ask questions about Datadog

A managed agent for read-only Datadog observability investigation.

User
Caller
  • chat
App
Agent
  • datadog-answerer
Governance
Gateway
  • datadog-readonly
Pool

datadog-answerer-pool

  • datadog-answerer-model
Tools

datadog

    What this template gives you

    • Interface

      A chat window, in your browser

      Use the included interface to send a request to this template.

    • Gateway

      datadog-readonly gateway

      This template sends its requests through datadog-readonly gateway, where its access rules and limits apply.

    • Model

      datadog-answerer-model

      This template uses datadog-answerer-model through the datadog-answerer-pool pool.

    Usage

    Hand this template to an AI agent to set up this template

    Node.js and npm to run npx.

    Dome CLI, installed with brew install dome-systems/tap/dome, then signed in with dome auth login.

    Docker Compose to run the companion app locally.

    1. 1

      Create a workspace

      dome workspaces create --name <workspace-name>

      The CLI creates and selects a workspace context for you.

    2. 2

      Confirm the workspace context

      dome context list

      The workspace you just created is already selected.

    3. 3

      Pull the template

      npx @domesystems/templates pull dome-systems/ai-agent-for-datadog@0.1.0 --dir ai-agent-for-datadog

      Downloads this immutable release and verifies its digest.

    4. 4

      Run the template

      npx @domesystems/templates up --dir ai-agent-for-datadog

      Imports it into Dome and starts the companion app.

    Dome import variables

    npx @domesystems/templates up imports the template into Dome and prompts for required values. For unattended runs, set them as DOME_IMPORT_VAR_… environment variables.

    Required values

    • DOME_IMPORT_VAR_anthropic_api_key

    Setup guide

    Follow this template's setup guidance for agent variables and upstream connections.

    # Configure Datadog

Before starting OAuth, a Datadog organization administrator must open
**Organization Settings → MCP OAuth Redirect URLs** and add this exact URL:

`https://api.domesystems.ai/oauth/callback`

Datadog rejects the consent flow with **Mismatching redirect URI** until that
allowlist entry exists. Dome uses Dynamic Client Registration, so no separate
Datadog OAuth client or client secret is needed. Dome requests Datadog's
published `mcp_all` scope during consent.

Before connecting, an organization administrator must also enable **MCP Access**
in Datadog. The authorizing test user needs **MCP Read** and the underlying
resource permissions (for example, Monitors Read); custom roles need those
permissions added explicitly. This template starts with Datadog's generally
available `core` toolset. Add the Preview `apm` toolset only after obtaining
Datadog's APM Preview access.

- `anthropic_api_key`: enter the Anthropic key used by this agent's model.

After saving, complete OAuth with a test user that has read access only to the selected services, logs, and dashboards. This template targets US1 and uses the `core` toolset.

    Runtime environment

    These variables are required to run the agent. During pull, .env.example is copied to .env when available. If they’re missing, npx @domesystems/templates up retrieves them from Dome and saves them in .env. Pass --provision to refresh them.

    No .env.example is included in this release.

    Agent instructions

    Investigate the connected Datadog account. Summarize logs, metrics, traces, monitors,
and service health. Do not modify monitors, dashboards, incidents, or integrations.