layout-doctor-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAYOUT_DOCTOR_CHROMIUM | No | Path to a Chromium executable. If not set, Playwright's bundled Chromium is used. |
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 |
|---|---|
| layout_checkA | HTMLをレンダリングしてレイアウトの破綻を検出する。検査専用でファイルは変更しない。 比較用のベースライン画像は不要。DOMの座標と文字の描画矩形を実測するため、 「どの要素が何ピクセルはみ出しているか」が数値で返る。 検出: 文字の重なり / 画面外や親からのはみ出し / overflow:hidden による切り捨て / 横スクロールの発生 / undefined・{{name}} 等の未展開 / 参照切れ / id重複 / 不可視テキスト 引数:
戻り値: summary(pass, errors, warnings, infos)と findings の配列。 各所見は check / severity / verdict / elements(selector, text, rect)/ evidence / suggest を持つ。 verdict は "static"(確定)か "candidate"(座標上は検出、可視性は未判定)。 対象外: デザインの評価、コントラスト比などのアクセシビリティ検査、前回との差分比較。 |
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 1 tool
Only one tool exists, so there is no possibility of confusion or incorrect selection. The tool uniquely targets layout checking with a clear and comprehensive role. Disambiguation is trivially perfect.
The single tool name 'layout_check' follows a clear verb-noun pattern (check the layout) and accurately describes its function. Since there is no other tool to compare patterns, the consistency is essentially unqualified, but a perfect 5 would require a larger set. A 4 reflects the lack of pattern evidence rather than any inconsistency.
The server has only one tool, which per the rubric is considered too few for a typical tool server. While the tool itself is comprehensive and covers many layout-checks, the extreme minimalism limits workflow flexibility and integration. This falls into the 'too few' category rather than the borderline 1-2 range.
The tool covers a wide range of layout-detection features (overlap, overflow, truncation, horizontal scroll, unresolved references, id duplication, invisible text), and explicitly excludes unrelated areas like accessibility and design evaluation. For its stated purpose of layout diagnostics, the surface is remarkably complete. However, the lack of any companion tools (e.g., to fix issues or compare against a baseline) creates a minor gap in a full workflow, so it doesn't earn a perfect 5.