What data can I access with Datadog MCP Server?
You can access monitors, dashboards, metrics metadata, events, logs (search and aggregation), and incidents. All tools provide read-only access to Datadog resources.
@GeLi2001
Basic information
MCP server interacts with the official Datadog API
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"datadog-mcp-server": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"datadog-mcp-server",
"--apiKey=your_api_key",
"--appKey=your_app_key"
]
}
}
}Fetch monitors with optional filtering
Get details of a specific monitor by ID
List all dashboards
Get a specific dashboard by ID
List available metrics
Get metadata for a specific metric
Fetch events within a time range
List incidents with optional filtering
Search logs with advanced query filtering
Perform analytics and aggregations on log data
A Model Context Protocol server that enables AI assistants to interact with the Datadog API. It provides tools for monitoring, dashboards, metrics, events, logs, and incidents using v1 and v2 APIs. Designed for developers managing Datadog resources through natural language interfaces.
Install globally via npm (npm install -g datadog-mcp-server) or clone the repository and build. Configure using environment variables (DD_API_KEY, DD_APP_KEY, DD_SITE) or command-line arguments (--apiKey, --appKey, --site). Add the server to your MCP client configuration (e.g., claude_desktop_config.json) with the required credentials.
You can access monitors, dashboards, metrics metadata, events, logs (search and aggregation), and incidents. All tools provide read-only access to Datadog resources.
You need a Datadog API key and an Application key. These can be scoped to minimum permissions using the listed required scopes (e.g., `monitors_read`, `dashboards_read`).
Yes. Specify the site using `DD_SITE` or `--site`. Supported regions include US (`datadoghq.com`), EU (`datadoghq.eu`), US3 (`ddog-gov.com`), US5 (`us5.datadoghq.com`), and AP1 (`ap1.datadoghq.com`). You can also set separate endpoints for logs and metrics.
Node.js version 16 or higher. The server is installed via npm and can be run with `npx`.
If you receive a 403 Forbidden error, verify your API and Application keys are correct, have necessary scopes, and that you are using the correct endpoint for your region. Check Claude Desktop's MCP logs for details.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Agent-Native Terminal
Comments