datadog mcp

Instructions

Implementation Reference

• src/tools/getDashboard.ts:27-43 (handler)

  The execute function implementing the core logic to fetch a specific Datadog dashboard by ID using the Datadog API client.
  execute: async (params: GetDashboardParams) => { try { const { dashboardId } = params; const apiInstance = new v1.DashboardsApi(configuration); const apiParams: v1.DashboardsApiGetDashboardRequest = { dashboardId: dashboardId }; const response = await apiInstance.getDashboard(apiParams); return response; } catch (error) { console.error(`Error fetching dashboard ${params.dashboardId}:`, error); throw error; } }
• src/index.ts:134-146 (registration)

  Registers the 'get-dashboard' tool with the MCP server, including description, Zod input schema, and wrapper that calls the handler's execute method.
  server.tool( "get-dashboard", "Get the complete definition of a specific Datadog dashboard by its ID. Returns all widgets, layout, and configuration details.", { dashboardId: z.string() }, async (args) => { const result = await getDashboard.execute(args); return { content: [{ type: "text", text: JSON.stringify(result) }] }; } );
• src/index.ts:137-139 (schema)

  Zod schema defining the input parameters for the tool: dashboardId as a required string.
  { dashboardId: z.string() },
• src/tools/getDashboard.ts:3-5 (schema)

  TypeScript type definition for the input parameters used in the handler.
  type GetDashboardParams = { dashboardId: string; };
• src/tools/getDashboard.ts:10-25 (helper)

  Initialization function that sets up the Datadog API client configuration with API keys and site.
  initialize: () => { const configOpts = { authMethods: { apiKeyAuth: process.env.DD_API_KEY, appKeyAuth: process.env.DD_APP_KEY } }; configuration = client.createConfiguration(configOpts); if (process.env.DD_SITE) { configuration.setServerVariables({ site: process.env.DD_SITE }); } },