oxilytics-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OXILYTICS_TOKEN | No | Your read-only API token | |
| OXILYTICS_ENV_FILE | No | Optional path to a file containing OXILYTICS_SERVER_URL and OXILYTICS_TOKEN | |
| OXILYTICS_SERVER_URL | No | Base URL of your OxiLytics instance, e.g. https://analytics.example.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| overviewA | Start here. Overall state of the OxiLytics instance. Reports which stores are configured, how many apps and products exist, totals for the last N days, and the outcome of recent sync runs. Answers "how are things doing" and "is anything broken" in a single call. Args: days: Look-back window for the totals. |
| list_appsA | List store listings, with ids, platform, rating and last sync time. Use this to find the app_id that other tools need, or to see which apps are not yet released. Args: search: Case-insensitive filter on the app name. unassigned: Show only listings not yet attached to a product. |
| list_productsA | List products with download and crash totals. A product groups one app across stores and platforms. Products are the business-level view; apps are the per-store listings underneath them. |
| metricsA | Totals for every metric over a date range, against the preceding period. Args: days: Look-back window, ignored when frm is given. frm: Start date YYYY-MM-DD. to: End date YYYY-MM-DD, defaults to yesterday. app_id: Restrict to one store listing. product_id: Restrict to one product. platform: Restrict to a platform, e.g. ios or android. store: Restrict to one store. |
| timeseriesA | A metric over time, bucketed by day, week or month. Use to spot trends, spikes, and the effect of a release. Args: metric: Which metric to plot. bucket: Time bucket size. days: Look-back window, ignored when frm is given. frm: Start date YYYY-MM-DD. to: End date YYYY-MM-DD. app_id: Restrict to one store listing. product_id: Restrict to one product. store: Restrict to one store. |
| top_countriesA | Ranked countries for a metric over a date range. Args: metric: Which metric to rank by. limit: How many countries to return. days: Look-back window. app_id: Restrict to one store listing. product_id: Restrict to one product. |
| reviewsA | User reviews, newest first, with optional filters. Use to read what users actually say, or to find complaints about a feature. Args: limit: How many reviews to return. rating: Comma-separated ratings, e.g. "1,2" for negative reviews only. country: Two-letter country code. query: Free-text search within the review body. app_id: Restrict to one store listing. product_id: Restrict to one product. |
| sync_runsA | Recent sync runs with status and row counts. Use to check whether data collection is working and when it last ran. Args: limit: How many runs to return. store: Restrict to one store. |
| sync_run_logA | The log of one sync run; the way to find out why a run produced no data. By default returns a summary that groups repeated messages, which is the fast way to see what happened across many apps. Args: run_id: Which run to inspect, from sync_runs. full: Return every line instead of the grouped summary. level: Only show lines at this level. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: overview summarizes overall state, list_apps and list_products enumerate entities, metrics provides totals, timeseries gives time-bucketed data, top_countries ranks by country, reviews returns user feedback, and sync_runs/sync_run_log cover data collection. Even the overlapping filter-heavy tools (metrics, timeseries, top_countries) are unambiguously differentiated by their output shape and descriptions.
All tool names use snake_case and are concise, but they mix conventions: list_apps and list_products use verb_noun, while others are bare nouns (metrics, timeseries, reviews) or compound nouns (top_countries, sync_run_log). The style is internally consistent and readable, but not strictly uniform.
With 9 tools, the server is well-scoped for a read-only analytics and monitoring domain. Each tool serves a distinct analytical or operational need, and none feel redundant or superficial. This is squarely within the ideal 3–15 range.
The tool surface covers the full lifecycle of the server's purpose: high-level health (overview), entity discovery (list_apps, list_products), data analysis (metrics, timeseries, top_countries), qualitative feedback (reviews), and operational diagnostics (sync_runs, sync_run_log). There are no obvious gaps for a read-only analytics tool—write operations are intentionally out of scope.