get_error_analytics

Instructions

Implementation Reference

• src/tools/analytics.tools.ts:556-586 (handler)

  The MCP tool handler for 'get_error_analytics'. It registers a tool with the MCP server, calls service.analytics.getErrorAnalytics with normalized params, maps data_points to {timestamp, total_errors}, and formats the response using formatGraphAnalytics.

  server.tool(
  	"get_error_analytics",
  	"Get error-count time-series data with summary.total_errors and per-bucket counts. Use this for high-level error trends; use get_error_rate_analytics for percentages, or get_error_status_codes_analytics and get_error_stacks_analytics for breakdowns.",
  	baseAnalyticsSchema,
  	async (params) => {
  		const analytics = await service.analytics.getErrorAnalytics(
  			normalizeAnalyticsParams(params as Record<string, unknown>),
  		);
  		const dataPoints = analytics.data_points.map((point) => ({
  			timestamp: point.timestamp,
  			total_errors: point.total,
  		}));
  		return {
  			content: [
  				{
  					type: "text",
  					text: JSON.stringify(
  						formatGraphAnalytics(
  							{
  								total_errors: analytics.summary.total,
  							},
  							dataPoints,
  						),
  						null,
  						2,
  					),
  				},
  			],
  		};
  	},
  );

• src/services/analytics.service.ts:123-136 (schema)

  Type definitions for ErrorAnalyticsResponse, ErrorDataPoint, and ErrorSummary used in the handler.

  export interface ErrorDataPoint {
  	timestamp: string;
  	total: number;
  }
  
  export interface ErrorSummary {
  	total: number;
  }
  
  export interface ErrorAnalyticsResponse {
  	object: "analytics-graph";
  	data_points: ErrorDataPoint[];
  	summary: ErrorSummary;
  }

• src/tools/analytics.tools.ts:264-277 (helper)

  Helper function formatGraphAnalytics used to structure the response with summary, point_count, and data_points.

  function formatGraphAnalytics(
  	summary: Record<string, unknown>,
  	dataPoints: Record<string, unknown>[],
  ): {
  	summary: Record<string, unknown>;
  	point_count: number;
  	data_points: Record<string, unknown>[];
  } {
  	return {
  		summary,
  		point_count: dataPoints.length,
  		data_points: dataPoints,
  	};
  }

• src/tools/analytics.tools.ts:15-35 (helper)

  The baseAnalyticsSchema Zod schema (fragment shown) used for input validation across all analytics tools including get_error_analytics.

  const baseAnalyticsSchema = {
  	time_of_generation_min: z
  		.string()
  		.describe(
  			"Start time for the analytics period (ISO8601 format, e.g., '2024-01-01T00:00:00Z')",
  		),
  	time_of_generation_max: z
  		.string()
  		.describe(
  			"End time for the analytics period (ISO8601 format, e.g., '2024-02-01T00:00:00Z')",
  		),
  	total_units_min: z.coerce
  		.number()
  		.positive()
  		.optional()
  		.describe("Minimum number of total tokens to filter by"),
  	total_units_max: z.coerce
  		.number()
  		.positive()
  		.optional()
  		.describe("Maximum number of total tokens to filter by"),

• src/tools/index.ts:110-125 (registration)

  Registration of 'get_error_analytics' in the ENTERPRISE_GATED_TOOL_NAMES set, marking it as an enterprise-only tool.

  const ENTERPRISE_GATED_TOOL_NAMES = new Set([
  	"get_cost_analytics",
  	"get_request_analytics",
  	"get_token_analytics",
  	"get_latency_analytics",
  	"get_error_analytics",
  	"get_error_rate_analytics",
  	"get_cache_hit_latency",
  	"get_cache_hit_rate",
  	"get_users_analytics",
  	"get_error_stacks_analytics",
  	"get_error_status_codes_analytics",
  	"get_user_requests_analytics",
  	"get_rescued_requests_analytics",
  	"get_feedback_analytics",
  	"get_feedback_models_analytics",