agentleFS
Sign inStart free
Cogni-AI-OUCogni-AI-OU/cogni-ai-agent-skills/datadog-mcp/SKILL.md

datadog-mcp

Skill4 starsChanged 6 months agoMITView on GitHub

Query observability data via Datadog MCP, selecting minimal toolsets to optimize context window and scope.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Execute Queries: Use targeted MCP tool calls to retrieve data.

    line 17
  2. Distinctive:

    If you require additional scopes to complete the task, check the full list of scopes (Datadog Role Permissions) and report to the user.

    line 52
  3. Distinctive:

    datadog-agent: Use when installing, configuring, or updating Datadog Agent.

    line 72

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

<!-- markdownlint-disable MD013 MD023 MD031 MD032 -->

Query Datadog telemetry (logs, metrics, traces, monitors, incidents, services, notebooks) directly via MCP to preserve agent context window and avoid context switching.

Core Process

  1. Identify Required Data: Determine the specific observability telemetry needed (e.g., traces vs. monitors).
  2. Select Minimal Toolset: Choose the narrowest toolset that provides the required data.
  3. Execute Queries: Use targeted MCP tool calls to retrieve data.
  4. Synthesize Findings: Analyze the telemetry within the current context.

Core Principles

  • Context Optimization: Aggressively minimize toolset surface area. Prefer specialized toolsets over the core toolset whenever possible.
  • MCP Exclusivity: Exclusively use MCP tools for telemetry. Never attempt SSH access to hosts or request UI navigation.

Commands / Usage Patterns

Load the appropriate toolset based on the task:

  • core: Broad access (logs, metrics, traces, dashboards, monitors, incidents, hosts, services, events, notebooks). Use only when multiple domains are needed simultaneously.
  • alerting: Monitor validation, monitor group search, monitor templates.
  • apm: Advanced trace analysis, span search, Watchdog insights, performance investigation.
  • cases: Case Management workflows (create/search/update, Jira linking).
  • dbm: Database Monitoring queries and investigations.
  • ddsql: Preview DDSQL tools for logs, metrics, RUM, spans, and infrastructure data.
  • error-tracking: Error Tracking issue search and retrieval.
  • feature-flags: Feature flag listing, creation, updates, and environment configuration.
  • llmobs: LLM Observability spans and experiment analysis.
  • product-analytics: Product Analytics query tooling.
  • networks: Cloud Network Monitoring and Network Device Monitoring analysis.
  • security: Security scans, security signals, and security findings analysis.
  • software-delivery: CI Visibility and Test Optimization analysis.
  • synthetics: Synthetics test retrieval and updates.
  • workflows: Workflow Automation listing, inspection, execution, and trigger updates.

Access Control

Application Key Scopes

Application Key Scopes restrict what applications can access in your Datadog data without granting new capabilities - they simply limit the scope of existing permissions.

If you require additional scopes to complete the task, check the full list of scopes (Datadog Role Permissions) and report to the user.

Reference

What to Avoid

  • Loading the core toolset by default when a narrow toolset (e.g., apm or alerting) is sufficient.
  • Reverting to manual Datadog UI navigation, SSH access, or raw curl requests (datadog-api) for standard telemetry retrieval when the MCP server is available.

Limitations

  • Query depth and visibility are constrained by the active Datadog role and the implemented MCP server capabilities.

Related Skills

  • datadog-agent: Use when installing, configuring, or updating Datadog Agent.
  • datadog-api: Execute raw Datadog API requests. Fallback when MCP lacks a specific capability or for administrative actions.

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.

Check your setup, free