metric-shift-mcp-server
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| metric_shift_inspect_dataA | 分析前にデータの中身を確認する。列の一覧、日時列の推定結果、日付範囲、次元(切り口)候補、指標候補を返す。metric_shift_localize を呼ぶ前にこのツールで列名と期間を確認することを推奨。 |
| metric_shift_localizeA | 「先週から売上(予約件数)が落ちた。どこで?」に答える。基準期間から曜日補正つきの予測値を作り、対象期間の実績との乖離がどの属性組合せ(例: 曜日=火 かつ 時間帯=夜、チャネル=web)に集中しているかを特定する。Squeeze(ISSRE 2019)アルゴリズムの独自実装。相関に基づく絞り込みであり因果の証明ではない。列名が不明な場合は先に metric_shift_inspect_data で確認すること。 |
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 2 tools
The two tools have clearly distinct purposes: one inspects data to provide context (columns, date ranges, candidates), while the other performs the actual shift localization. There is no overlap or ambiguity between them.
Both tools follow the exact same verb_noun pattern with a consistent prefix 'metric_shift_'. The names clearly indicate action (inspect/localize) and domain, making them predictable and easy to navigate.
With only 2 tools, the server feels slightly thin but is well-scoped for a narrow, specialized purpose: metric shift analysis. The two tools cover the entire intended workflow (inspect then localize), so the count is appropriate for the niche.
The tool surface covers the essential workflow: inspection before localization, which is explicitly recommended. Minor gaps exist (e.g., no tool for comparing periods or exporting results), but for the stated purpose of answering 'where did the metric drop?', the coverage is sufficient.