Enables interaction with Datadog's observability platform, providing access to metrics, logs, APM traces, infrastructure data, dashboards, monitors, incidents, service catalog, SLOs, and usage statistics through natural language queries.
Referenced as an architectural pattern that this implementation follows, suggesting similar capabilities for interacting with Jira's issue tracking and project management features.
Datadog MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Datadog's observability platform through natural language.
Features
Metrics: Query time-series data, list metrics, get metadata
Logs: Search and filter log events
APM: Access trace data, service maps, dependencies
Infrastructure: Host information, container data, process metrics
Dashboards: List and read dashboard configurations
Monitors: Alert rules and status information
Incidents: Incident tracking and management
Service Catalog: Service definitions and relationships
SLOs: Service level objectives and compliance data
Usage: Account usage statistics
Installation
From Source
Using Docker
Configuration
Required Environment Variables
Optional Environment Variables
Regional Endpoints
For different Datadog regions:
US:
https://api.datadoghq.com
(default)EU:
https://api.datadoghq.eu
US3:
https://api.us3.datadoghq.com
US5:
https://api.us5.datadoghq.com
AP1:
https://api.ap1.datadoghq.com
Usage
Command Line
Docker
Claude Desktop Integration
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/claude/claude_desktop_config.json
Or use the native installation:
OpenAPI Specification
The server requires the Datadog v2 API OpenAPI specification to be placed at:
src/datadog_mcp/specs/datadog-v2.yaml
You can obtain this specification from:
Community-maintained specifications
Security
By default, the server runs with security filtering enabled (MCP_ENABLE_SECURITY_FILTERING=true
), which restricts operations to read-only access. This includes:
Allowed Operations
GET requests to query metrics, logs, traces, etc.
Reading dashboards, monitors, and configurations
Searching and filtering data
Viewing usage statistics
Blocked Operations
All POST, PUT, PATCH, DELETE operations
User and API key management
Organization settings modifications
Any destructive actions
To disable security filtering (not recommended for production):
Example Interactions
Once configured, you can interact with Datadog through natural language:
"Show me the error rate for my web service over the last hour"
"List all active monitors that are alerting"
"Get the CPU usage metrics for production hosts"
"Show me recent incidents in the platform team"
"What's our log volume usage this month?"
"Find traces with high latency in the payment service"
"Show me the service dependencies for the API gateway"
Development
Setup Development Environment
Running Tests
Building Docker Image
Architecture
The server follows the same architectural patterns as the Jira MCP implementation:
FastMCP 2.0: Leverages automatic tool generation from OpenAPI specifications
Security-First: Default read-only access with configurable filtering
Environment Configuration: All settings via environment variables
Docker-First: Containerized deployment for consistency
Transport Flexibility: Supports both stdio and WebSocket transports
Troubleshooting
Authentication Errors
Ensure both
DATADOG_API_KEY
andDATADOG_APP_KEY
are set correctlyVerify your keys have the necessary permissions in Datadog
Check you're using the correct regional endpoint
Connection Issues
Verify your network can reach the Datadog API
Check if you need to configure proxy settings
Ensure the timeout is sufficient for your queries
Missing Tools
Verify the OpenAPI specification is present in
src/datadog_mcp/specs/
Check the server logs for any specification loading errors
Ensure the specification version matches your Datadog API version
Contributing
Contributions are welcome! Please feel free to submit issues and pull requests.
License
MIT License - see LICENSE file for details
Credits
Based on the Jira MCP implementation pattern.
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
A Model Context Protocol server that enables AI assistants to interact with Datadog's observability platform through natural language.
Related MCP Servers
- -securityFlicense-qualityA comprehensive Model Context Protocol server implementation that enables AI assistants to interact with file systems, databases, GitHub repositories, web resources, and system tools while maintaining security and control.Last updated -331
- -securityFlicense-qualityA lightweight Model Context Protocol server that enables creating, managing, and querying model contexts with integrated Datadog metrics and monitoring.Last updated -
- AsecurityAlicenseAqualityA template for building Model Context Protocol servers that allow AI assistants to interact with custom data and services through queryable resources and specialized tools.Last updated -6MIT License