ezstat-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EZSTAT_API_KEY | Yes | Your EzStat API key (the 'ezkey'). Required. Never hardcode. Never log. | |
| EZSTAT_BASE_URL | No | Override for staging / self-hosted. | https://api.ezstat.dev |
| EZSTAT_QUERY_PATH | No | Ask-Your-Data path. | /api/v1/query |
| EZSTAT_TIMEOUT_MS | No | Per-request timeout in milliseconds. | 10000 |
| EZSTAT_INGEST_PATH | No | Override if you proxy the EZ endpoint. | /api/ez |
| EZSTAT_STATS_LIST_PATH | No | Stats list path. | /api/v1/stats |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| track_metricA | Record a metric point your app "produced". Use this whenever the surrounding code emits a counter or gauge — e.g. on a page view, a successful checkout, or a measured latency. Counters are +N (default +1), values are gauges (e.g. 42.5 ms). |
| ask_ezstatA | Ask a natural-language question about the account's metrics. This is the agent-read path: send a question like "what spiked yesterday?" or "compare signups vs cancellations last 7 days" and EzStat returns a grounded answer plus the underlying data it used. |
| read_statA | Read a single stat: latest value, recent series, and basic summary (count/min/max/avg/sum). Use this for a structured read of one metric — prefer |
| list_statsA | List the account's metrics — names and types. Call this first when you don't know what stats exist in the account. |
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 4 tools
Each tool has a clear, distinct role: track_metric writes, read_stat does structured reads of a single metric, ask_ezstat handles free-form natural-language queries, and list_stats discovers available metrics. The overlap between read_stat and ask_ezstat is explicitly addressed in their descriptions, making misselection unlikely.
Most tools follow a clear verb_noun pattern: track_metric, read_stat, list_stats. ask_ezstat also follows verb_noun but uses a product-specific noun, which is slightly inconsistent with the generic metric-related nouns used elsewhere. Overall the pattern is still predictable and readable.
Four tools is on the smaller side but appropriate for the focused scope of tracking and querying metrics. Each tool serves a core need without redundancy, though the set could be expanded with e.g. delete_metric or batch operation tools.
The tool surface covers the essential lifecycle: record (track_metric), read single (read_stat), query over many (ask_ezstat), and discover (list_stats). It lacks explicit update/delete operations, but for a metrics tracking server these are often unnecessary, and agents can work around this limitation.