Datadog

You can run and use the Datadog MCP Server to access a wide range of Datadog monitoring capabilities through MCP clients like Claude Desktop. It exposes pipelines, logs, metrics, monitors, service definitions, and team data, enabling end-to-end observability workflows from a single MCP endpoint.

How to use

You interact with the Datadog MCP Server by launching the MCP client configuration that points to the server runtime. Use the provided tools to list pipelines, retrieve logs, query metrics, manage monitors and SLOs, fetch service definitions, and view team memberships. You can run the server directly from the MCP runner you use (UVX or UV) or via a local development setup. In Claude Desktop, configure a server entry that runs the MCP client and points to the Datadog MCP Server runner, then issue commands like listing pipelines, querying metrics, or retrieving service definitions to build your observability workflows.

How to install

export DD_API_KEY="your-datadog-api-key"
export DD_APP_KEY="your-datadog-application-key"

# UVX Direct Run (latest)
uvx --from git+https://github.com/shelfio/datadog-mcp.git datadog-mcp

# UVX Direct Run (specific version, production)
uvx --from git+https://github.com/shelfio/datadog-mcp.git@v0.0.5 datadog-mcp

# UVX Direct Run (branch)
uvx --from git+https://github.com/shelfio/datadog-mcp.git@main datadog-mcp

# Development quick run (clone local and run)
# (clone repository first, then run the server command below)
export DD_API_KEY="your-datadog-api-key" 
export DD_APP_KEY="your-datadog-application-key"
uv run ddmcp/server.py

# Podman (optional containerized run)
podman run -e DD_API_KEY="your-datadog-api-key" -e DD_APP_KEY="your-datadog-application-key" -i $(podman build -q https://github.com/shelfio/datadog-mcp.git)

Prerequisites you need to install before running the server include a supported Python environment and the MCP runtime tooling used to fetch and run the server. Ensure you have access to your Datadog API Key and Application Key before starting a local or remote MCP instance.

Configuration

Environment variables you will typically set for operation include the Datadog credentials and region. These variables are used by the server to authenticate with Datadog and to route requests to the appropriate Datadog site.

{
  "mcpServers": {
    "datadog": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/shelfio/datadog-mcp.git", "datadog-mcp"],
      "env": {
        "DD_API_KEY": "your-datadog-api-key",
        "DD_APP_KEY": "your-datadog-application-key"
      }
    }
  },
  "envVars": [
    {"name": "DD_API_KEY", "description": "Datadog API Key", "required": true, "example": null},
    {"name": "DD_APP_KEY", "description": "Datadog Application Key", "required": true, "example": null},
    {"name": "DD_SITE", "description": "Datadog site/region", "required": false, "example": "datadoghq.com"}
  ]
}

If you prefer a local development setup, you can also run the MCP server with a local path and the standard MCP runner as shown in the development flow.

Examples of common tasks

• Show me all CI pipelines for a repository
• Get error logs for a service in the last 4 hours
• List all available AWS metrics
• Get the latest metrics for a specific metric grouped by account
• Retrieve all fields for a metric like system.cpu.user
• List all service definitions in my organization
• Get the definition for a specific service
• List all teams and their members
• Show all monitors for a service
• List SLOs with less than 99% uptime
• Extract pipeline fingerprints for Terraform configurations

Security and access notes

Keep your Datadog credentials secure. Use environment-level protection and avoid hard-coding keys in configuration files. Rotate API and Application Keys regularly and restrict their permissions to what is necessary for MCP operations.

Troubleshooting

If the MCP server fails to start, verify that your Datadog keys are valid and that the runner has network access to Datadog services. Check that the command and arguments match the runtime you are using (UVX or UV) and ensure the working directory is correct for local development runs.

Available tools

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

Retrieves all values for a specific field of a metric.

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.

get_teams

Lists teams and their members.