datadog-mcp-server: Instructions file for Claude Code

CLAUDE.md

datadog-mcp-server CLAUDE.md is an instructions file for Claude Code from us-all/datadog-mcp-server. It costs 4,091 tokens per session, scanned A, original, MIT.

Repository instructions for a custom Datadog MCP server. MCP is a standard way for an AI assistant to call tools; this server connects those tools to Datadog monitoring data.

In plain words
What is it for?
Use it when building, running, or changing the TypeScript server that queries Datadog metrics, application traces, user data, and other APIs.
Why use it?
It gives an agent the project context, commands, technology choices, and file layout needed to work on the server correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is us-all/datadog-mcp-server's own configuration. It tells Claude Code how to work on datadog-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything datadog-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to us-all/datadog-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/us-all/datadog-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/us-all/datadog-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for datadog-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/us-all/datadog-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/us-all/datadog-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/us-all/datadog-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/us-all/datadog-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,091 This file is loaded in full into every session.
When invoked 4,091 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.04091 $0.04091
Opus 5 $0.02046 $0.02046
Sonnet 5 $0.00818 $0.00818
Haiku 4.5 $0.00409 $0.00409

Measured 6d ago against content hash 0ada38e5d9c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

datadog-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Custom Datadog MCP (Model Context Protocol) server that gives Claude access to Datadog monitoring APIs. Replaces the limited community MCP server by adding time-series metrics queries, APM/Traces, RUM data, and full Datadog API coverage via the official SDK.

Tech Stack

  • Runtime: Node.js 18+ with TypeScript (strict mode)
  • Package Manager: pnpm
  • MCP SDK: @modelcontextprotocol/sdk (^1.27.1)
  • Datadog Client: @datadog/datadog-api-client (^1.59.0)
  • Validation: zod
  • Config: dotenv

Build & Run Commands

pnpm install          # Install dependencies
pnpm run build        # Compile TypeScript → dist/
pnpm run dev          # Watch mode (auto-rebuild)
node dist/index.js    # Run the MCP server

Architecture

This is an MCP server running as a subprocess, configured via .mcp.json. The data flow is:

Claude AI → MCP Protocol → index.ts (server) → tools/*.ts → Datadog API Client → Datadog API

Key Source Files

  • src/index.ts — MCP server entry point, 156 tool registrations
  • src/config.ts — Environment variable loading (DD_API_KEY, DD_APP_KEY, DD_SITE)
  • src/client.ts — Datadog API client initialization using official SDK
  • src/tools/utils.tswrapToolHandler error handling wrapper for all tools
  • src/tools/ — One file per tool category, each exporting schema + handler

Tool Pattern

Each tool file follows the same pattern:

  1. Define zod input schema with .describe() on every field
  2. Call Datadog API via official SDK client
  3. Transform response to a readable format
  4. Handler is wrapped with wrapToolHandler() in index.ts for error handling

Tool Categories (156 tools)

File Tools
metrics.ts query-metrics, get-metrics, get-metric-metadata, list-active-metrics, list-metric-tags
monitors.ts get-monitors, get-monitor, create-monitor, update-monitor, delete-monitor, mute-monitor, validate-monitor
dashboards.ts get-dashboards, get-dashboard, create-dashboard, update-dashboard, delete-dashboard
logs.ts search-logs, aggregate-logs, send-logs
events.ts get-events, post-event
incidents.ts get-incidents, get-incident, search-incidents, create-incident, update-incident, delete-incident
apm.ts search-spans
rum.ts search-rum-events, aggregate-rum, list-rum-applications, get-rum-application, create-rum-application, update-rum-application, delete-rum-application
rum-metrics.ts list-rum-metrics, get-rum-metric, create-rum-metric, update-rum-metric, delete-rum-metric
rum-retention-filters.ts list-rum-retention-filters, get-rum-retention-filter, create-rum-retention-filter, update-rum-retention-filter, delete-rum-retention-filter
hosts.ts list-hosts, get-host-totals
slos.ts list-slos, get-slo, get-slo-history
synthetics.ts list-synthetics, get-synthetics-result, trigger-synthetics, create-synthetics-test, update-synthetics-test, delete-synthetics-test
downtimes.ts list-downtimes, create-downtime, cancel-downtime
security.ts search-security-signals, get-security-signal, list-security-rules, get-security-rule, delete-security-rule, list-security-suppressions, get-security-suppression, create-security-suppression, delete-security-suppression
account.ts get-usage-summary, list-users
notebooks.ts list-notebooks, get-notebook
oncall.ts get-team-oncall, get-oncall-schedule
services.ts list-services, get-service-definition
containers.ts list-containers
processes.ts list-processes
audit.ts search-audit-logs
cases.ts list-cases, get-case, create-case, update-case-status
errors.ts list-error-tracking-issues, get-error-tracking-issue
ci.ts search-ci-pipelines, aggregate-ci-pipelines, search-ci-tests, aggregate-ci-tests
networks.ts list-network-devices, get-network-device
dora.ts send-dora-deployment, send-dora-incident
teams.ts list-teams, get-team, create-team, update-team, delete-team, get-team-members
logs-metrics.ts list-logs-metrics, get-logs-metric, create-logs-metric, update-logs-metric, delete-logs-metric
spans-metrics.ts list-spans-metrics, get-spans-metric, create-spans-metric, update-spans-metric, delete-spans-metric
slo-corrections.ts list-slo-corrections, get-slo-correction, create-slo-correction, update-slo-correction, delete-slo-correction
apm-retention-filters.ts list-apm-retention-filters, get-apm-retention-filter, create-apm-retention-filter, update-apm-retention-filter, delete-apm-retention-filter
status-pages.ts list-status-pages, get-status-page, create-status-page, update-status-page, delete-status-page, publish-status-page, unpublish-status-page, list-status-page-components, get-status-page-component, create-status-page-component, update-status-page-component, delete-status-page-component, list-status-page-degradations, get-status-page-degradation, create-status-page-degradation, update-status-page-degradation, delete-status-page-degradation, list-status-page-maintenances, get-status-page-maintenance, create-status-page-maintenance, update-status-page-maintenance
fleet.ts list-fleet-agents, get-fleet-agent-info, list-fleet-agent-versions, list-fleet-tracers, list-fleet-deployments, get-fleet-deployment, create-fleet-deployment-configure, create-fleet-deployment-upgrade, cancel-fleet-deployment, list-fleet-schedules, get-fleet-schedule, create-fleet-schedule, update-fleet-schedule, delete-fleet-schedule, trigger-fleet-schedule

Read the full file on GitHub · 148 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 148 lines · 4,091 tokens per session scan A 0ada38e5d9c7

Subscribe to this mod's changes

datadog-mcp-server CLAUDE.md is an instructions file published in the GitHub repository us-all/datadog-mcp-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 4,091 tokens to every session, about $0.0205 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens