Datadog MCP Server

An MCP server for the Datadog API, allowing you to search logs and traces.

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

- 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

- 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

- 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

- 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)

- 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")

- Aggregation results in buckets, each including:

- Bucket ID
- Group by values (if groupBy is specified)
- Computed values based on the aggregation method

- Processing time (elapsed)
- Request ID
- Status
- Warnings (if any)

You need to set up Datadog API and application keys:
- Get your API key and application key from theDatadog API Keys page
- Install dependencies in the datadog-mcp project:

npm install # or pnpm install

{ "mcpServers": { "datadog": { "command": "node", "args": [ "/path/to/datadog-mcp/build/index.js" ], "env": { "DD_API_KEY": "<YOUR_DATADOG_API_KEY>", "DD_APP_KEY": "<YOUR_DATADOG_APP_KEY>" } } } }

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

{ "mcpServers": { "datadog": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "DD_API_KEY", "-e", "DD_APP_KEY", "datadog-mcp" ], "env": { "DD_API_KEY": "<YOUR_DATADOG_API_KEY>", "DD_APP_KEY": "<YOUR_DATADOG_APP_KEY>" } } } }

For quick installation in VS Code, configure your settings:
- Open User Settings (JSON) in VS Code (Ctrl+Shift+P→Preferences: Open User Settings (JSON))
- Add the following configuration:

{ "mcp": { "servers": { "datadog": { "command": "node", "args": [ "/path/to/datadog-mcp/build/index.js" ], "env": { "DD_API_KEY": "<YOUR_DATADOG_API_KEY>", "DD_APP_KEY": "<YOUR_DATADOG_APP_KEY>" } } } } }

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

{ "mcp": { "servers": { "datadog": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "DD_API_KEY", "-e", "DD_APP_KEY", "datadog-mcp" ], "env": { "DD_API_KEY": "<YOUR_DATADOG_API_KEY>", "DD_APP_KEY": "<YOUR_DATADOG_APP_KEY>" } } } } }

Alternatively, you can add this to a.vscode/mcp.jsonfile in your workspace (without themcpkey):

{ "servers": { "datadog": { "command": "node", "args": [ "/path/to/datadog-mcp/build/index.js" ], "env": { "DD_API_KEY": "<YOUR_DATADOG_API_KEY>", "DD_APP_KEY": "<YOUR_DATADOG_APP_KEY>" } } } }

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

{ "servers": { "datadog": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "DD_API_KEY", "-e", "DD_APP_KEY", "datadog-mcp" ], "env": { "DD_API_KEY": "<YOUR_DATADOG_API_KEY>", "DD_APP_KEY": "<YOUR_DATADOG_APP_KEY>" } } } }

Fetch logs, metrics, traces, and events from the Chronosphere observability platform.

Interact with the Datadog API to monitor your cloud infrastructure, applications, and logs.

The Datadog MCP Server acts as a bridge between your observability data in Datadog and any AI agents that support the Model Context Protocol (MCP).

Provides comprehensive Datadog monitoring capabilities through MCP clients. Requires Datadog API and Application keys.

Provides comprehensive Datadog monitoring capabilities through any MCP client.

Retrieve logs from the Mezmo observability platform.

Kubernetes observability and diagnostics MCP server for cluster health, workload diagnosis, logs, events, topology, audit findings, and remediation actions.

Access and visualize logs from SolarWinds Observability.

Seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster.

Provides access to OpenTelemetry traces and metrics through Logfire.