Datadog MCP Server

Datadog MCP Server

English (This Document) | 日本語

MCP Server for Datadog API, enabling log search, trace span search, and trace span aggregation functionalities.

Features

• Log Search: Search and retrieve logs from Datadog with flexible query options
• Trace Span Search: Search for distributed trace spans with various filtering options
• Trace Span Aggregation: Aggregate trace spans by different dimensions for analysis

Tools

1. search_logs
   • Search for logs in Datadog
   • Inputs:
     • filterQuery (optional string): Query string to search logs (default: "*")
     • filterFrom (optional number): Search start time as UNIX timestamp in seconds (default: 15 minutes ago)
     • filterTo (optional number): Search end time as UNIX timestamp in seconds (default: current time)
     • pageLimit (optional number): Maximum number of logs to retrieve (default: 25, max: 1000)
     • pageCursor (optional string): Pagination cursor for retrieving additional results
   • Returns: Formatted text containing:
     • Search conditions (query and time range)
     • Number of logs found
     • Next page cursor (if available)
     • Log details including:
       • Service name
       • Tags
       • Timestamp
       • Status
       • Message (truncated to 300 characters)
       • Host
       • Important attributes (http.method, http.url, http.status_code, error)
2. search_spans
   • Search for trace spans in Datadog
   • Inputs:
     • filterQuery (optional string): Query string to search spans (default: "*")
     • filterFrom (optional number): Search start time as UNIX timestamp in seconds (default: 15 minutes ago)
     • filterTo (optional number): Search end time as UNIX timestamp in seconds (default: current time)
     • pageLimit (optional number): Maximum number of spans to retrieve (default: 25, max: 1000)
     • pageCursor (optional string): Pagination cursor for retrieving additional results
   • Returns: Formatted text containing:
     • Search conditions (query and time range)
     • Number of spans found
     • Next page cursor (if available)
     • Span details including:
       • Service name
       • Timestamp
       • Resource name
       • Duration (in seconds)
       • Host
       • Environment
       • Type
       • Important attributes (http.method, http.url, http.status_code, error)
3. aggregate_spans
   • Aggregate trace spans in Datadog by specified dimensions
   • Inputs:
     • filterQuery (optional string): Query string to filter spans for aggregation (default: "*")
     • filterFrom (optional number): Start time as UNIX timestamp in seconds (default: 15 minutes ago)
     • filterTo (optional number): End time as UNIX timestamp in seconds (default: current time)
     • groupBy (optional string[]): Dimensions to group by (e.g., ["service", "resource_name", "status"])
     • aggregation (optional string): Aggregation method - "count", "avg", "sum", "min", "max", "pct" (default: "count")
     • interval (optional string): Time interval for time series data (only when type is "timeseries")
     • type (optional string): Result type, either "timeseries" or "total" (default: "timeseries")
   • Returns: Formatted text containing:
     • Aggregation results in buckets, each including:
       • Bucket ID
       • Group by values (if groupBy is specified)
       • Computed values based on the aggregation method
     • Additional metadata:
       • Processing time (elapsed)
       • Request ID
       • Status
       • Warnings (if any)

Setup

You need to set up Datadog API and application keys:

1. Get your API key and application key from the Datadog API Keys page
2. Install dependencies in the datadog-mcp project:
   npm install # or pnpm install
3. Build the TypeScript project:
   npm run build # or pnpm run build

Docker Setup

You can build using Docker with the following command:

Usage with Claude Desktop

To use this with Claude Desktop, add the following to your claude_desktop_config.json:

If you're using Docker, you can configure it like this:

Usage with VS Code

For quick installation in VS Code, configure your settings:

1. Open User Settings (JSON) in VS Code (Ctrl+Shift+P → Preferences: Open User Settings (JSON))
2. Add the following configuration:

If you're using Docker, you can configure it like this:

Alternatively, you can add this to a .vscode/mcp.json file in your workspace (without the mcp key):

If you're using Docker, you can configure it like this: