Skip to main content
Glama
Haydebug

roblox-analytics-mcp

by Haydebug

query_metric

Query any Roblox experience analytics metric as a time series. Get summary stats, breakdowns, filters, and outlier detection for retention, engagement, and monetization.

Instructions

Query one analytics metric as a time series. This is the core read tool — everything the Analytics Query API exposes is reachable through it.

Returns, per series: summary statistics (first, last, min, max, mean, median, stdDev, sum, percent change, trend per bucket), outlier buckets beyond 2.5 standard deviations, any buckets the API returned no data for, and the raw data points.

Use breakdown to split into one series per dimension value, and filter to narrow the population. The request is validated against the metric's documented capabilities before it is sent, so mistakes come back as a clear message rather than an opaque 400.

Note aggregationHint: for rates, averages, and percentiles the sum of buckets is not a meaningful number — read mean instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoCap on breakdown series, ranked by value. Only valid with granularity 'None' and a breakdown — the documented way to find the top N segments.
filterNoNarrow results to specific dimension values.
metricYesExact, case-sensitive metric name. Use list_metrics to find one.
endTimeNoExclusive end. Defaults to today's UTC midnight so only complete buckets are returned — pass 'now' if you want the partial current day included.
lastDaysNoShorthand for the last N complete UTC days. Cannot be combined with startTime.
breakdownNoDimensions to split by, one series per value, e.g. ['Platform']. Must be supported by the metric — see describe_metric.
startTimeNoInclusive start. RFC 3339 (2026-01-01T00:00:00Z), a date (2026-01-01), or relative (-30d, -12w, -6mo, -2y, -48h, today, yesterday).
universeIdNoRoblox universe (experience) ID, or a saved alias. Optional when a default universe is configured — use get_server_status to check, or find_universes to look one up.
granularityNoTime bucket size. Defaults to OneDay, or the metric's coarsest supported option when it has no daily bucket.
maxDataPointsNoCap on data points returned per series (most recent kept). Default 400.
skipValidationNoSend the request even if it fails local validation. Use only if you believe the API supports something the bundled catalog does not list.
includeDataPointsNoInclude raw per-bucket values. Default true. Turn off for a summary-only view.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Despite having no annotations, the description provides unusually detailed behavior: client-side request validation, per-series summary statistics, trend and outliers, raw data points, no-data buckets, error messaging, default granularity, endTime exclusive semantics, lastDays shorthand, includeDataPoints toggle, and maxDataPoints cap, aggregation hint for rates/averages/percentiles.

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?

The description is well-packed and dense but not bloated. It methodically describes params, returns, defaults, validation and aggregations and stays organized; each sentence pays rent.

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?

Has a high degree of richness and the API is complex: no output schema, but the return shape is described per series; multiple edge cases covered; the tool is positioned against siblings; no annotations; but descriptions are complete for the API's surface.

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?

Schema coverage is 100% across 12 parameters, so parameters are already well described in the JSON schema. The description adds value beyond schema by documenting default server time, relative time shorthands, excluded endTime, break-down/filter semantics, and the validation-and-clear-error behavior.

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?

Specific verb+resource: 'Query one analytics metric as a time series'; explicitly positioned as 'the core read tool' with 'everything the Analytics Query API exposes is reachable through it', distinguishing it as central versus the sibling metrics tools.

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

Usage Guidelines4/5

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

Strong context: 'Core read tool' implies primary choice; states validation against metric capabilities avoids opaque errors. Does not explicitly name sibling alternatives or when to avoid, but the core-tool positioning differentiates.

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

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/Haydebug/Roblox-MCP-Analytics'

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