Dd MCP Server

Most monitoring and observability work still happens through a UI a human drives. Dd MCP MCP server moves it into the conversation instead. A Model Context Protocol (MCP) server that provides comprehensive Datadog monitoring capabilities through Claude Desktop and other MCP clients.

The short version

• CI/CD Pipeline Management — List CI pipelines, extract fingerprints
• Service Logs Analysis — Retrieve and analyze service logs with environment and time filtering
• Metrics Monitoring — Query any Datadog metric with flexible filtering, aggregation, and field discovery
• Monitoring & Alerting — List and manage Datadog monitors and Service Level Objectives (SLOs)
• Service Definitions — List and retrieve detailed service definitions with metadata, ownership, and configuration
• Team Management — List teams, view member details, and manage team information

The tools it exposes

The server publishes 13 tools. What each one is for:

• Recommendations — See GitHub releases for all available versions
• list_ci_pipelines — Lists all CI pipelines registered in Datadog with filtering options
• get_pipeline_fingerprints — Extracts pipeline fingerprints for use in Terraform service definitions
• list_metrics — Lists all available metrics from Datadog for metric discovery
• get_metrics — Queries any Datadog metric with flexible filtering and aggregation
• get_metric_fields — Retrieves all available fields (tags) for a specific metric
• get_metric_field_values — The get_metric_field_values tool exposed by this server
• list_service_definitions — Lists all service definitions from Datadog with pagination and filtering
• get_service_definition — Retrieves the definition of a specific service with detailed metadata
• get_service_logs — Retrieves service logs with comprehensive filtering capabilities
• list_monitors — Lists all Datadog monitors with comprehensive filtering options
• list_slos — Lists Service Level Objectives (SLOs) from Datadog with filtering capabilities

Getting it running

The server ships on PyPI as Direct, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What it needs from you

Configuration is passed through the environment: DD_API_KEY, DD_APP_KEY, DD_SITE. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

This sits in the monitoring and observability group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Dd MCP's toolset — Recommendations, list_ci_pipelines, get_pipeline_fingerprints and 10 more — is a fair guide to whether it matches your workflow. It is maintained by magistersart; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Dd MCP.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.