Skip to main content
Glama
nks-hub

rybbit-mcp

by nks-hub

Error Tracking

rybbit_get_errors
Read-onlyIdempotent

Retrieve and analyze error tracking data from Rybbit Analytics. View error types and counts, examine individual instances with stack traces, or monitor trends over time to identify and debug issues.

Instructions

Get error tracking data. Workflow: (1) type='names' to see error types and counts, (2) type='events' with errorMessage to see individual instances with stack traces, (3) type='timeseries' with errorMessage to see trends over time.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
siteIdYesSite ID (numeric ID or domain identifier)
startDateNoStart date in ISO format (YYYY-MM-DD)
endDateNoEnd date in ISO format (YYYY-MM-DD)
timeZoneNoIANA timezone (e.g., Europe/Prague). Default: UTC
filtersNoArray of filters. Example: [{parameter:'browser',type:'equals',value:['Chrome']},{parameter:'country',type:'equals',value:['US','DE']}]
pastMinutesStartNoAlternative to dates: minutes ago start (e.g., 60 = last hour)
pastMinutesEndNoAlternative to dates: minutes ago end (default 0 = now)
pageNoPage number, 1-indexed (default: 1)
limitNoResults per page (default: 20-50 depending on endpoint, max 200)
typeNo'names' for error type summary with counts, 'events' for individual error instances with stack traces, 'timeseries' for error count trends over time for a specific error. Default: names
errorMessageNoError message filter (required for type='events' and type='timeseries'). Use type='names' first to discover error messages.
bucketNoTime bucket for timeseries type (default: day)

Implementation Reference

  • The async handler function for the rybbit_get_errors tool, which processes arguments, calls the appropriate RybbitClient endpoint based on the 'type' parameter, and formats the response.
      async (args) => {
        try {
          const { siteId, type, errorMessage, bucket, page, limit, ...rest } = args as {
            siteId: string;
            type?: "names" | "events" | "timeseries";
            errorMessage?: string;
            bucket?: string;
            page?: number;
            limit?: number;
            startDate?: string;
            endDate?: string;
            timeZone?: string;
            filters?: Array<{
              parameter: string;
              type: string;
              value: (string | number)[];
            }>;
            pastMinutesStart?: number;
            pastMinutesEnd?: number;
          };
    
          const params = client.buildAnalyticsParams({ ...rest, page, limit, bucket });
    
          if (type === "timeseries") {
            if (!errorMessage) {
              return {
                content: [{ type: "text" as const, text: "Error: errorMessage is required for type='timeseries'. Use type='names' first to discover error messages, then pass one to errorMessage." }],
                isError: true,
              };
            }
            params.errorMessage = errorMessage;
            const data = await client.get<unknown[]>(
              `/sites/${siteId}/error-bucketed`,
              params
            );
            return {
              content: [{ type: "text" as const, text: truncateResponse(data) }],
            };
          }
    
          if (type === "events") {
            if (!errorMessage) {
              return {
                content: [{ type: "text" as const, text: "Error: errorMessage is required for type='events'. Use type='names' first to discover error messages, then pass one to errorMessage." }],
                isError: true,
              };
            }
            params.errorMessage = errorMessage;
            const data = await client.get<ErrorEvent[]>(
              `/sites/${siteId}/error-events`,
              params
            );
            return {
              content: [{ type: "text" as const, text: truncateResponse(data) }],
            };
          }
    
          const data = await client.get<ErrorName[]>(
            `/sites/${siteId}/error-names`,
            params
          );
          return {
            content: [{ type: "text" as const, text: truncateResponse(data) }],
          };
        } catch (err) {
          const message = err instanceof Error ? err.message : String(err);
          return {
            content: [{ type: "text" as const, text: `Error: ${message}` }],
            isError: true,
          };
        }
      }
    );
  • Registration of the rybbit_get_errors tool with the MCP server, including the definition of the input schema using Zod.
    server.registerTool(
      "rybbit_get_errors",
      {
        title: "Error Tracking",
        description:
          "Get error tracking data. Workflow: (1) type='names' to see error types and counts, (2) type='events' with errorMessage to see individual instances with stack traces, (3) type='timeseries' with errorMessage to see trends over time.",
        annotations: {
          readOnlyHint: true,
          idempotentHint: true,
          openWorldHint: true,
          destructiveHint: false,
        },
        inputSchema: {
          ...analyticsInputSchema,
          ...paginationSchema,
          type: z
            .enum(["names", "events", "timeseries"])
            .optional()
            .describe(
              "'names' for error type summary with counts, 'events' for individual error instances with stack traces, 'timeseries' for error count trends over time for a specific error. Default: names"
            ),
          errorMessage: z
            .string()
            .optional()
            .describe("Error message filter (required for type='events' and type='timeseries'). Use type='names' first to discover error messages."),
          bucket: z
            .enum(["minute", "five_minutes", "hour", "day", "week", "month"])
            .optional()
            .describe("Time bucket for timeseries type (default: day)"),
        },
      },
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, safe operation. The description adds valuable behavioral context: the discovery pattern (names → specific errors), and what data each mode returns (counts vs. stack traces vs. trends). It does not mention rate limits or pagination behavior, preventing a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences total. The first states the core purpose; the second presents a numbered workflow that efficiently communicates the three operational modes and their dependencies. No redundancy or extraneous text—every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema, the description effectively compensates by describing the conceptual return values for each type (counts, stack traces, trends). With 12 parameters fully documented in the schema, the description appropriately focuses on the high-level workflow rather than repeating parameter details. Minor gap: does not mention filtering or pagination capabilities, though these are schema-documented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the baseline is 3. The description elevates this by explaining the semantic relationship between parameters: type='events' and type='timeseries' require errorMessage, and type='names' must be used first to discover valid errorMessage values. This workflow context is not captured by the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves error tracking data and immediately distinguishes it from sibling analytics tools by specifying unique error-specific outputs: error types/counts, individual instances with stack traces, and timeseries trends. The resource (errors) and action (get) are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The workflow explicitly prescribes a three-step sequence: (1) use type='names' for discovery, (2) use type='events' with errorMessage for details, (3) use type='timeseries' for trends. This provides clear when-to-use guidance for each mode and identifies the prerequisite relationship (must discover errorMessage via names before using other types).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nks-hub/rybbit-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server