G2 Product Analytics MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| list_metricsA | List governed metrics available to the analytics agent. |
| get_metric_definitionC | Return the governed definition and metadata for one metric. |
| get_metricA | Calculate one governed metric for an inclusive date range (YYYY-MM-DD). |
| compare_review_completion_by_dimensionC | Compare review completion rate across an approved dimension. |
| compare_periodsC | Compare a governed metric between two periods and calculate absolute/relative change. |
| diagnose_review_completion_changeA | Diagnose a review-completion change by comparing device segments across two periods. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| product_analytics_investigation | Reusable instructions for a trustworthy product analytics investigation. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| metrics_catalog | Governed metric catalog: definitions, owners, source tables, dimensions and freshness. |
TDQS
Scored across 6 tools
Tools are mostly distinct: list_metrics, get_metric_definition, and get_metric cover metric discovery, definition, and calculation, while the three comparison/diagnosis tools have clear scopes. Some potential confusion exists between compare_review_completion_by_dimension and diagnose_review_completion_change, but their descriptions differentiate by dimension vs. device segment.
All tool names follow a consistent verb_noun snake_case pattern (list, get, compare, diagnose). No mixed conventions or vague verbs are present, making the naming predictable and clear.
With 6 tools, the server is well-scoped for product analytics. Each tool serves a distinct purpose without redundancy, and the count falls comfortably within the ideal range.
The tool surface covers the core workflow: discover metrics, understand definitions, calculate values, compare across periods/dimensions, and diagnose changes. Minor gaps exist, such as lacking a general dimension breakdown for arbitrary metrics (only review completion has one), but the set is largely complete for its stated purpose.