Datadog MCP Server

A Model Context Protocol (MCP) server that provides comprehensive Datadog monitoring capabilities through Claude Desktop and other MCP clients.

- 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

Choose your preferred method to run the Datadog MCP server:

export DD_API_KEY="your-datadog-api-key" DD_APP_KEY="your-datadog-application-key" # Latest version (HEAD) uvx --from git+https://github.com/shelfio/datadog-mcp.git datadog-mcp # Specific version (recommended for production) uvx --from git+https://github.com/shelfio/datadog-mcp.git@v0.0.5 datadog-mcp # Specific branch uvx --from git+https://github.com/shelfio/datadog-mcp.git@main datadog-mcp

export DD_API_KEY="your-datadog-api-key" DD_APP_KEY="your-datadog-application-key" git clone https://github.com/shelfio/datadog-mcp.git /tmp/datadog-mcp && cd /tmp/datadog-mcp && uv run ddmcp/server.py

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)

- Python 3.13+
- UV package manager (includes uvx)
- Datadog API Key and Application Key

- Podman
- Datadog API Key and Application Key

When using UVX, you can specify exact versions for reproducible deployments:

- Latest:git+https://github.com/shelfio/datadog-mcp.git(HEAD)
- Specific Tag:git+https://github.com/shelfio/datadog-mcp.git@v0.0.5
- Branch:git+https://github.com/shelfio/datadog-mcp.git@main
- Commit Hash:git+https://github.com/shelfio/datadog-mcp.git@59f0c15

- Production: Use specific tags (e.g.,@v0.0.5) for stability
- Development: Use latest or specific branch for newest features
- Testing: Use commit hashes for exact reproducibility

SeeGitHub releasesfor all available versions.

{ "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" } } } }

Specific version (recommended for production):

{ "mcpServers": { "datadog": { "command": "uvx", "args": ["--from", "git+https://github.com/shelfio/datadog-mcp.git@v0.0.5", "datadog-mcp"], "env": { "DD_API_KEY": "your-datadog-api-key", "DD_APP_KEY": "your-datadog-application-key" } } } }

For EU region(seeMulti-Region Supportfor other regions):

{ "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", "DD_SITE": "datadoghq.eu" } } } }

For development with local cloned repository:

git clone https://github.com/shelfio/datadog-mcp.git cd datadog-mcp

{ "mcpServers": { "datadog": { "command": "uv", "args": ["run", "ddmcp/server.py"], "cwd": "/path/to/datadog-mcp", "env": { "DD_API_KEY": "your-datadog-api-key", "DD_APP_KEY": "your-datadog-application-key" } } } }

Install and run directly from GitHub without cloning:

export DD_API_KEY="your-datadog-api-key" export DD_APP_KEY="your-datadog-application-key" # Latest version uvx --from git+https://github.com/shelfio/datadog-mcp.git datadog-mcp # Specific version (recommended for production) uvx --from git+https://github.com/shelfio/datadog-mcp.git@v0.0.5 datadog-mcp

git clone https://github.com/shelfio/datadog-mcp.git cd datadog-mcp

export DD_API_KEY="your-datadog-api-key" export DD_APP_KEY="your-datadog-application-key" uv run ddmcp/server.py

podman run -e DD_API_KEY="your-key" -e DD_APP_KEY="your-app-key" -i $(podman build -q https://github.com/shelfio/datadog-mcp.git)

The server provides these tools to Claude:

Lists all CI pipelines registered in Datadog with filtering options.

- repository(optional): Filter by repository name
- pipeline_name(optional): Filter by pipeline name
- format(optional): Output format - "table", "json", or "summary"

Extracts pipeline fingerprints for use in Terraform service definitions.

- repository(optional): Filter by repository name
- pipeline_name(optional): Filter by pipeline name
- format(optional): Output format - "table", "json", or "summary"

Lists all available metrics from Datadog for metric discovery.

- filter(optional): Filter to search for metrics by tags (e.g., 'aws:', 'env:', 'service:web')
- limit(optional): Maximum number of metrics to return (default: 100, max: 10000)

Queries any Datadog metric with flexible filtering and aggregation.

- metric_name(required): The metric name to query (e.g., 'aws.apigateway.count', 'system.cpu.user')
- time_range(optional): "1h", "4h", "8h", "1d", "7d", "14d", "30d"
- aggregation(optional): "avg", "sum", "min", "max", "count"
- filters(optional): Dictionary of filters to apply (e.g., {'service': 'web', 'env': 'prod'})
- aggregation_by(optional): List of fields to group results by
- format(optional): "table", "summary", "json", "timeseries"

Retrieves all available fields (tags) for a specific metric.

- metric_name(required): The metric name to get fields for
- time_range(optional): "1h", "4h", "8h", "1d", "7d", "14d", "30d"

Retrieves all values for a specific field of a metric.

- metric_name(required): The metric name
- field_name(required): The field name to get values for
- time_range(optional): "1h", "4h", "8h", "1d", "7d", "14d", "30d"

Lists all service definitions from Datadog with pagination and filtering.

- page_size(optional): Number of service definitions per page (default: 10, max: 100)
- page_number(optional): Page number for pagination (0-indexed, default: 0)
- schema_version(optional): Filter by schema version (e.g., 'v2', 'v2.1', 'v2.2')
- format(optional): Output format - "table", "json", or "summary"

Retrieves the definition of a specific service with detailed metadata.

- service_name(required): Name of the service to retrieve
- schema_version(optional): Schema version to retrieve (default: "v2.2", options: "v1", "v2", "v2.1", "v2.2")
- format(optional): Output format - "formatted", "json", or "yaml"

Retrieves service logs with comprehensive filtering capabilities.

- service_name(required): Name of the service
- time_range(required): "1h", "4h", "8h", "1d", "7d", "14d", "30d"
- environment(optional): "prod", "staging", "backoffice"
- log_level(optional): "INFO", "ERROR", "WARN", "DEBUG"
- format(optional): "table", "text", "json", "summary"

Lists all Datadog monitors with comprehensive filtering options.

- name(optional): Filter monitors by name (substring match)
- tags(optional): Filter monitors by tags (e.g., 'env:prod,service:web')
- monitor_tags(optional): Filter monitors by monitor tags (e.g., 'team:backend')
- page_size(optional): Number of monitors per page (default: 50, max: 1000)
- page(optional): Page number (0-indexed, default: 0)
- format(optional): Output format - "table", "json", or "summary"

Lists Service Level Objectives (SLOs) from Datadog with filtering capabilities.

- query(optional): Filter SLOs by name or description (substring match)
- tags(optional): Filter SLOs by tags (e.g., 'team:backend,env:prod')
- limit(optional): Maximum number of SLOs to return (default: 50, max: 1000)
- offset(optional): Number of SLOs to skip (default: 0)
- format(optional): Output format - "table", "json", or "summary"

- team_name(optional): Filter by team name
- include_members(optional): Include member details (default: false)
- format(optional): "table", "json", "summary"

"Show me all CI pipelines for the shelf-api repository" "Get error logs for the content service in the last 4 hours" "List all available AWS metrics" "What are the latest metrics for aws.apigateway.count grouped by account?" "Get all available fields for the system.cpu.user metric" "List all service definitions in my organization" "Get the definition for the user-api service" "List all teams and their members" "Show all monitors for the web service" "List SLOs with less than 99% uptime" "Extract pipeline fingerprints for Terraform configuration"

Datadog operates in multiple regions. Set theDD_SITEenvironment variable to connect to your Datadog region:

export DD_SITE="datadoghq.eu" export DD_API_KEY="your-api-key" export DD_APP_KEY="your-app-key" uvx --from git+https://github.com/shelfio/datadog-mcp.git datadog-mcp

SeeDatadog's Getting Started with Sitesfor more information.
- Log in to your Datadog account
- Go toOrganization Settings→API Keys
- Create or copy yourAPI Key(this is yourDD_API_KEY)
- Go toOrganization Settings→Application Keys
- Create or copy yourApplication Key(this is yourDD_APP_KEY)

ThousandEyes Network Performance Monitoring MCP Server