Log inSubmit server
Datadog MCP Server logo

Datadog MCP Server

by us-all

Connects AI agents to Datadog for observability queries, incident analysis, SLO management, fleet automation, and status-page operations.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Datadog MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "us-all-datadog-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@us-all/datadog-mcp"
      ],
      "env": {
        "DD_API_KEY": "YOUR_VALUE_HERE",
        "DD_APP_KEY": "YOUR_VALUE_HERE",
        "DD_SITE": "YOUR_VALUE_HERE",
        "DD_ALLOW_WRITE": "YOUR_VALUE_HERE",
        "DD_TOOLS": "YOUR_VALUE_HERE",
        "DD_DISABLE": "YOUR_VALUE_HERE",
        "MCP_TRANSPORT": "YOUR_VALUE_HERE",
        "MCP_HTTP_TOKEN": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The us-all/datadog-mcp-server MCP server exposes Datadog APIs through 163 MCP tools covering metrics, monitors, logs, APM, RUM, incidents, SLOs, fleet automation, and status pages. It runs locally over stdio by default or uses Streamable HTTP with bearer authentication for remote clients and ChatGPT Apps SDK deployments. Aggregation tools combine related Datadog lookups into structured responses, while prompts support incident triage, monitor-noise audits, RUM investigations, and slow-trace analysis. Reach for it when read-only observability is not enough, or when you need self-hosting, broader API coverage, or controlled write access.

Use cases

  • Investigate active incidents across monitors, APM errors, and recent deployments
  • Audit noisy monitors by alert frequency and mean time to recovery
  • Analyze RUM error spikes and affected user sessions
  • Manage SLOs and inspect remaining error budgets
  • Schedule Datadog fleet rollouts and maintain status pages

Key features

  • 163 Datadog tools across 16 categories
  • Aggregation tools for monitor and SLO investigations
  • SLO CRUD and correction support
  • Fleet automation and status-page lifecycle tools
  • stdio and Streamable HTTP transports
  • Configurable tool loading and response-field projection

Tools80

What Datadog MCP Server lets your agent do. Expand a tool for its parameters.

Self-reported~351 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

16/17 checks healthy over the last 79d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · @us-all/datadog-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
npm downloads1kPackage downloads in the last 30 days.
Last commit3mo agoMost recent push to the default branch.
Tools exposed80Callable tools this server registers over MCP.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How Datadog MCP Server works

What us-all/datadog-mcp-server MCP server does

The us-all/datadog-mcp-server MCP server connects an MCP-compatible AI client to Datadog using API and Application keys. Its 163 tools are organized across 16 categories, including metrics, monitors, dashboards, logs, APM, RUM, incidents, security, synthetics, CI, infrastructure, fleet operations, status pages, on-call, teams, and account data.

The server supports both investigation and operational workflows. Read operations can retrieve telemetry and configuration, while selected mutations remain disabled unless explicitly enabled. Available write areas include monitors, dashboards, SLOs, synthetics, downtime, cases, DORA events, fleet operations, status pages, and security-related actions.

How it works

A client starts the package with stdio by default, which fits local Claude Desktop or Claude Code configurations. Setting MCP_TRANSPORT=http exposes a Streamable HTTP endpoint at /mcp; requests use bearer authentication when MCP_HTTP_TOKEN is configured. /health provides a public liveness endpoint. The HTTP mode can support remote deployments and ChatGPT Apps SDK use cases.

Two aggregation tools reduce multi-step investigation work. analyze-monitor-state and slo-compliance-snapshot combine several Datadog requests into one structured result and report partial failures through a caveats array. Four MCP prompts provide reusable workflows: incident triage, monitor-noise analysis, RUM error-spike investigation, and slow-trace investigation. Read-only MCP resources are also available for monitors, dashboards, SLOs, incidents, services, teams, synthetics tests, and hosts.

Setup and configuration

Install through npx, Docker, or a source build. Provide DD_API_KEY and DD_APP_KEY to authenticate with Datadog. DD_SITE selects the Datadog region and defaults to us5.datadoghq.com; supported values include US1, US3, US5, EU1, and AP1 sites.

Writes are blocked by default. Set DD_ALLOW_WRITE=true before enabling mutations. Use DD_TOOLS to load only selected categories, or DD_DISABLE to omit categories when no allowlist is present. DD_TOOLS takes precedence over DD_DISABLE.

For HTTP deployments, set MCP_TRANSPORT=http, provide MCP_HTTP_TOKEN, and optionally adjust MCP_HTTP_PORT or MCP_HTTP_HOST. MCP_HTTP_SKIP_AUTH=true is available when another reverse proxy supplies authentication.

Tools and capabilities

  • Query and manage Datadog metrics, monitors, dashboards, logs, APM, RUM, incidents, SLOs, synthetics, and infrastructure data.
  • Create, update, and delete SLOs and SLO corrections when write access is enabled.
  • Automate fleet deployments and schedules through 15 fleet tools.
  • Manage status-page components, degradations, and maintenances through 21 status-page tools.
  • Use extractFields to project selected response fields.
  • Discover available tools at runtime with the search-tools meta-tool.
  • Invoke four workflow prompts and read supported Datadog entities through MCP resource URIs.

Limitations and notes

The us-all/datadog-mcp-server MCP server requires valid Datadog credentials and appropriate permissions. Its default read-only behavior means write operations do not work until DD_ALLOW_WRITE=true is set. Enabling writes gives an agent access to mutation tools, so deployments should scope categories and credentials accordingly.

Loading every category exposes a large tool schema. The README reports approximately 25,200 schema tokens for the default configuration; restricting categories with DD_TOOLS reduces that context. The slo-compliance-snapshot visual card is intended for ChatGPT clients, while Claude clients receive the same underlying JSON content. The server is self-hosted rather than a managed Datadog service, and HTTP deployments require their own authentication and network controls.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Datadog MCP Server

us-all/datadog-mcp-server is an MCP server that connects AI clients to Datadog through API and Application keys. It provides 163 tools for metrics, monitors, logs, APM, RUM, incidents, SLOs, fleet automation, status pages, and related operations, with read-only defaults and optional write access.

Install it with npx, Docker, or a source build. Configure `DD_API_KEY`, `DD_APP_KEY`, and optionally `DD_SITE`; for npx, run `npx -y @us-all/datadog-mcp`. The README includes configurations for Claude Desktop, Claude Code, Docker, and building with pnpm.

Set `DD_ALLOW_WRITE=true` before starting the server. Writes are disabled by default, and the setting enables supported mutations such as monitor, dashboard, SLO, synthetics, fleet, status-page, and security operations.

It documents Claude Desktop and Claude Code for stdio, plus Streamable HTTP for remote clients and ChatGPT Apps SDK deployments.

Related MCP servers

All in Monitoring All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewDatadog MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/us-all-datadog-mcp-server?style=directory)](https://allmcps.com/mcp/us-all-datadog-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/us-all-datadog-mcp-server"><img src="https://allmcps.com/api/badge/us-all-datadog-mcp-server?style=directory" alt="Datadog MCP Server on AllMCPs" /></a>