蓝湖 Design Schema MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LANHU_COOKIE | No | Lanhu browser session cookie directly (not recommended, prefer LANHU_COOKIE_FILE). | |
| LANHU_COOKIE_FILE | No | Path to a file containing the Lanhu browser session cookie (absolute path recommended). |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| lanhu_get_designsA | [第一步] 获取蓝湖项目的 UI 设计图清单(index/id/名称/封面 URL/封面尺寸)。preview_size 是封面尺寸,不是设计画布;画布尺寸必须读取 Design IR meta.canvas。后续用返回的 index 或 id 调 lanhu_get_design_schema / lanhu_get_design_slices。 |
| lanhu_get_design_previewA | 获取单张设计图的预览图片,用于确认整体视觉、图层是否烧录文字等。预览图不是几何权威来源;尺寸、坐标、颜色仍以 lanhu_get_design_schema 和 slices 为准。 |
| lanhu_search_design_nodesA | 分页检索单张设计图的轻量节点目录,返回 id/路径/几何/文案/DS 身份/visible。包含 full/summary 默认裁剪的隐藏节点;大型稿或需要定位 node_ids 时优先使用。 |
| lanhu_get_design_slicesA | 获取单张设计图的切图清单:PNG/SVG 下载地址、logical_size(1x 逻辑尺寸)、position(画布坐标,量间距用)、stored_size(实际存储倍率尺寸)。off_canvas=true 仅表示切图与目标画布不相交;是否使用以及资源如何落地由目标端决定。 |
| lanhu_get_design_schemaA | [主要设计信息源] 获取单张设计图的 Design IR:节点层级、绝对/相对坐标、文字内容与字体、颜色/渐变/圆角/阴影、设计系统组件身份(component 字段,含选中/未选中等状态语义)。坐标是平台中立的 1x 设计逻辑单位,不包含目标端生产布局语义。full 响应过大会自动降级 summary;需要 transform/vector/token 等原始字段时,先用 lanhu_search_design_nodes 定位节点,再用 detail=exact + node_ids 分区读取。exact 会保留命中子树中的隐藏和零尺寸状态节点。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/andyjin5/lanhu-schema-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server