roblox-analytics-mcp
It lets you query Roblox experience analytics through MCP. Capabilities:
List ~150 supported analytics metrics with names, categories, granularities, retention, and dimensions.
Query time-series metrics (DAU, revenue, retention, playtime, crash rates, funnels, custom events, data store usage, etc.) for a universe with granularity, date range, breakdown dimensions, and filters.
Discover actual dimension values (countries, platforms, funnel names, event names, place IDs) for a metric and date range.
Poll pending long-running queries via get_operation.
Works locally via stdio or remotely via Cloudflare Worker over HTTP for claude.ai.
Stores API key locally, with env var fallback; read-only analytics access.
Provides tools for querying Roblox experience analytics, including DAU, revenue, retention, playtime, crash rates, funnels, custom events, and data store usage through the Open Cloud Analytics API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@roblox-analytics-mcp What was my DAU by platform for the last 30 days in universe 123456?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
roblox-analytics-mcp
A local MCP server that lets AI agents (Claude Code, Codex, etc.) query Roblox experience analytics — DAU, revenue, retention, playtime, crash rates, funnels, custom events, data store usage, and more — through the Open Cloud Analytics API.
Runs entirely on your machine. Your API key is stored locally and never leaves your computer.
Tools
Tool | What it does |
| Browse the ~150 supported metrics with their exact names, categories, supported granularities, retention windows, and supported dimensions. Filter by category or keyword. |
| Query a metric time series for a universe: pick a granularity ( |
| Discover which values a dimension actually has (countries, platforms, funnel names, custom event names, place IDs, …) for a metric and date range. |
| Poll a slow query that came back with |
Slow queries are polled automatically for up to 60 seconds (configurable via pollTimeoutSeconds).
If a query still isn't finished, the pending operation's path is returned so the agent can
call get_operation later.
Metric categories
Retention, Engagement, Monetization, Acquisition, Performance, Economy, Funnels, CustomEvents, Thumbnails, SpeechToText, TextToSpeech, Matchmaking, DataStore, MemoryStore, Safety, Advertising.
Standard metrics keep ~4 years of data; performance, data store, and memory store metrics keep 28 days;
matchmaking keeps 90 days. Ranges longer than two years only support OneWeek, OneMonth, or None.
Example prompts
"What was my DAU by platform for the last 30 days in universe 123456?"
"Compare revenue by country for August vs September."
"Which funnel steps have the highest churn in my onboarding funnel?"
"Show client crash rate per hour for the last 24 hours, broken down by PlaceVersion."
Related MCP server: Google Analytics MCP Server
Setup
1. Get an Open Cloud API key
Go to the Creator Dashboard → Open Cloud → API Keys.
Create a key and add the universe-analytics API system.
Give it the
universe.analytics:readscope for the universes you want to query.
This key only needs read access to analytics — nothing else.
2. Install
npm install -g @frrazers/roblox-analytics-mcp(Or clone this repo and run npm install && npm run build, then use node dist/cli.js as the command.)
3. Store your key
roblox-analytics-mcp setupThis prompts for your key (hidden input) and saves it to your OS config directory. No secrets end up in any shared config file. Check it worked with:
roblox-analytics-mcp status4. Connect it to Claude Code
Either register it:
claude mcp add roblox-analytics -- roblox-analytics-mcpor add a .mcp.json to your project (safe to commit — it contains no secret):
{
"mcpServers": {
"roblox-analytics": {
"command": "roblox-analytics-mcp"
}
}
}The tools appear as mcp__roblox-analytics__* in your next session; /mcp shows status.
Remote server for claude.ai (custom connector)
claude.ai (web, desktop, mobile) can't run local stdio servers, only remote ones over HTTP. The
worker/ directory is the same four tools served over MCP Streamable HTTP from a Cloudflare Worker.
cd worker
npm install
npx wrangler deploy
echo "<your Open Cloud key>" | npx wrangler secret put ROBLOX_API_KEY
echo "<a long random string>" | npx wrangler secret put MCP_SECRETThe endpoint is https://<worker>.workers.dev/mcp/<MCP_SECRET>. Add it in claude.ai under
Customize → Connectors → Add custom connector with no OAuth settings.
Custom connectors only support OAuth or no auth, so the secret path is the access control:
anyone with the full URL can query the universes that key is scoped to (read-only). Rotate it
by putting a new MCP_SECRET. Long queries are capped at 25 s of polling per tool call; the
agent resumes with get_operation if a query is still running.
Managing your key
Command | Action |
| Store or replace the key |
| Delete the stored key |
| Show whether a key is configured and where it came from |
A key stored by setup takes precedence. If you haven't run setup, the ROBLOX_API_KEY environment variable is used as a fallback (handy for CI).
Notes on the API
Metric names are case-sensitive (
DailyActiveUsers, notdailyactiveusers). The server warns you before sending if a name, granularity, or dimension doesn't match its local catalog, but still forwards the request in case the catalog is behind the live API.startTimeis inclusive andendTimeis exclusive, both RFC 3339 UTC.A 429 with code 3000 means the data-point budget was exceeded: shorten the range, coarsen the granularity, or reduce breakdowns.
License
MIT
Available Tools
4 toolsget_operationA
Check on a long-running analytics query. Use this when query_metrics or list_dimension_values returned done: false; pass the 'path' from that response. Returns the operation with 'done' and, once finished, the 'response' payload.
Inputs: path (required).
list_dimension_valuesA
Discover the actual values a dimension takes for a metric in a universe over a date range, e.g. which Country codes, Platform names, FunnelName values, CustomEventName values, or Place IDs have data. Use the returned values in query_metrics filters or to understand breakdown results. Returns { values: [{ dimension, values: [{ value }] }] }.
Inputs: metric (required), endTime (required), startTime (required), dimensions (required), +5 more.
list_metricsA
List the analytics metrics you can query, with each metric's exact (case-sensitive) name, human label, category, supported granularities, data retention in days, and supported breakdown/filter dimensions. Call this first to pick a metric and check which granularity and dimensions it accepts. Filter by category or search by keyword to keep the output small.
Inputs: search, category.
query_metricsA
Query a time series for one analytics metric of a Roblox universe (experience): DAU, revenue, retention, playtime, crash rate, funnels, custom events, and more. Returns data points bucketed by granularity, optionally broken down by dimensions (e.g. Platform, Country) and filtered. Each data point has a UTC 'time', a numeric 'value' (or 'stringValues' for text metrics), and may carry a 'status' of Valid, Projected, or NotStatisticallySignificant. Slow queries are polled automatically; if the response has done: false, call get_operation with its 'path'. Requires an API key with the universe.analytics:read scope.
Inputs: metric (required), endTime (required), startTime (required), universeId (required), +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a distinct responsibility: listing available metrics, querying metric time series, discovering dimension values, and polling async operations. There is no overlap in purpose; descriptions clearly separate the two data-retrieval tools.
All tool names follow a consistent verb_noun pattern (list_metrics, query_metrics, list_dimension_values, get_operation). The naming style is uniform and predictable.
Four tools is an appropriate size for an analytics-focused server: discovery, query, dimension exploration, and async operation handling cover the necessary workflow without bloat. Each tool earns its place.
The set covers the full analytics query lifecycle: find a metric, inspect its dimensions, run the query, and retrieve results for long-running operations. There are no obvious dead ends or missing core capabilities.
Maintenance
Related MCP Connectors
Lets AI agents analyze API metrics, request logs, and traces, and manage apps and alerts.
Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime.
Read-only Google Search Console and Google Analytics for AI agents.
Read-only analytics for Convex apps, queryable via MCP from Claude, Cursor, and other clients.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to access website analytics, including visitor sessions, UX friction, conversion funnels, and anomaly alerts.632 PyPIMIT
- AlicenseAqualityDmaintenanceEnables AI assistants to query Google Analytics accounts, properties, and run reports using natural language through the Admin and Data APIs.62Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to query Google Analytics 4 data, including listing accounts and properties, running historical and real-time reports with customizable metrics and dimensions.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to query a privacy-focused analytics service for aggregate stats, breakdowns, realtime visitors, and time-series trends across cloud or self-hosted deployments. It also provides connectivity checks and guided analytics playbooks.8MIT