Integrations
Provides access to Datadog's monitoring, dashboard, metrics, events, logs, and incident management features through direct API integration. Enables querying monitors, viewing dashboards, retrieving metrics metadata, searching logs with advanced filtering, and managing incidents.
Required as a runtime environment (version 16 or higher) for running the Datadog MCP server, enabling server-side JavaScript execution for API interactions.
Used for package installation and management of the Datadog MCP server, allowing easy global installation via the npm registry.
Datadog MCP Server
A Model Context Protocol (MCP) server for interacting with the Datadog API.
Features
- Monitoring: Access monitor data and configurations
- Dashboards: Retrieve and view dashboard definitions
- Metrics: Query available metrics and their metadata
- Events: Search and retrieve events within timeframes
- Logs: Search logs with advanced filtering and sorting options
- Incidents: Access incident management data
- API Integration: Direct integration with Datadog's v1 and v2 APIs
- Comprehensive Error Handling: Clear error messages for API and authentication issues
- Service-Specific Endpoints: Support for different endpoints for logs and metrics
Prerequisites
- Node.js (version 16 or higher)
- Datadog account with:
- API key - Found in Organization Settings > API Keys
- Application key - Found in Organization Settings > Application Keys
Installation
Via npm (recommended)
From Source
- Clone this repository
- Install dependencies:Copy
- Build the project:Copy
Configuration
You can configure the Datadog MCP server using either environment variables or command-line arguments.
Environment Variables
Create a .env
file with your Datadog credentials:
Note: DD_LOGS_SITE
and DD_METRICS_SITE
are optional and will default to the value of DD_SITE
if not specified.
Command-line Arguments
Basic usage with global site setting:
Advanced usage with service-specific endpoints:
Note: Site arguments don't need https://
- it will be added automatically.
Regional Endpoints
Different Datadog regions have different endpoints:
- US (Default):
datadoghq.com
- EU:
datadoghq.eu
- US3 (GovCloud):
ddog-gov.com
- US5:
us5.datadoghq.com
- AP1:
ap1.datadoghq.com
Usage with Claude Desktop
Add this to your claude_desktop_config.json
:
For more advanced configurations with separate endpoints for logs and metrics:
Locations for the Claude Desktop config file:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%/Claude/claude_desktop_config.json
Usage with MCP Inspector
To use with the MCP Inspector tool:
Available Tools
The server provides these MCP tools:
- get-monitors: Fetch monitors with optional filtering
- get-monitor: Get details of a specific monitor by ID
- get-dashboards: List all dashboards
- get-dashboard: Get a specific dashboard by ID
- get-metrics: List available metrics
- get-metric-metadata: Get metadata for a specific metric
- get-events: Fetch events within a time range
- get-incidents: List incidents with optional filtering
- search-logs: Search logs with advanced query filtering
- aggregate-logs: Perform analytics and aggregations on log data
Examples
Example: Get Monitors
Example: Get a Dashboard
Example: Search Logs
Example: Aggregate Logs
Example: Get Incidents
Troubleshooting
If you encounter a 403 Forbidden error, verify that:
- Your API key and Application key are correct
- The keys have the necessary permissions to access the requested resources
- Your account has access to the requested data
- You're using the correct endpoint for your region (e.g.,
datadoghq.eu
for EU customers)
Debugging
If you encounter issues, check Claude Desktop's MCP logs:
Common issues:
- 403 Forbidden: Authentication issue with Datadog API keys
- API key or App key format invalid: Ensure you're using the full key strings
- Site configuration errors: Make sure you're using the correct Datadog domain
- Endpoint mismatches: Verify that service-specific endpoints are correctly set if you're using separate domains for logs and metrics
License
MIT
You must be authenticated.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Tools
for tracing and monitoring
- Features
- Prerequisites
- Installation
- Configuration
- Usage with MCP Inspector
- Available Tools
- Examples
- Troubleshooting
- Debugging
- License
Related Resources
Related MCP Servers
- -securityFlicense-qualityProvides access to PyTorch CI/CD analytics data including workflows, jobs, test runs, and log analysis through an MCP interface.Last updated -Python
- AsecurityFlicenseAqualityAn MCP server for searching and visualizing SolarWinds Observability logs, allowing users to query log data with filtering options and generate visual representations of log events over time.Last updated -215TypeScript
- -securityAlicense-qualityProvides Claude with real-time system monitoring capabilities, including CPU, memory, disk, network, battery, and internet speed metrics.Last updated -TypeScriptMIT License
- -securityAlicense-qualityA lightweight server that provides real-time system information including CPU, memory, disk, and GPU statistics for monitoring and diagnostic purposes.Last updated -PythonMIT License