Lanhu MCP Server

一个功能强大的 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) 服务器,专为 AI 编程时代设计,完美支持蓝湖(Lanhu)设计协作平台。

Local serverstdioPython

What is the Lanhu MCP MCP server?

Connect Lanhu MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. 一个功能强大的 Model Context Protocol (MCP) 服务器,专为 AI 编程时代设计,完美支持蓝湖(Lanhu)设计协作平台。. The lanhu mcp mcp server is what makes that connection.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • lanhu_resolve_invite_link — 解析邀请链接
  • lanhu_get_pages — 获取原型页面列表
  • lanhu_get_ai_analyze_page_result — 分析原型页面内容
  • lanhu_get_designs — 获取UI设计图列表
  • lanhu_get_ai_analyze_design_result — 分析UI设计图
  • lanhu_get_design_slices — 获取切图信息
  • lanhu_say — 发布留言
  • lanhu_say_list — 查看留言列表
  • lanhu_say_detail — 查看留言详情
  • lanhu_say_edit — 编辑留言
  • lanhu_say_delete — 删除留言
  • lanhu_get_members — 查看协作者

Credentials and setup notes

Configuration is passed through the environment: LANHU_USER_NAME, LANHU_USER_ROLE, LANHU_COOKIE, FEISHU_WEBHOOK_URL, SERVER_HOST, SERVER_PORT, DATA_DIR, HTTP_TIMEOUT. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Where it fits

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Lanhu MCP's toolset — lanhu_resolve_invite_link, lanhu_get_pages, lanhu_get_ai_analyze_page_result and 9 more — is a fair guide to whether it matches your workflow. It is maintained by dsphper; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Lanhu MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Lanhu MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
lanhu_resolve_invite_link解析邀请链接
lanhu_get_pages获取原型页面列表
lanhu_get_ai_analyze_page_result分析原型页面内容
lanhu_get_designs获取UI设计图列表
lanhu_get_ai_analyze_design_result分析UI设计图
lanhu_get_design_slices获取切图信息
lanhu_say发布留言
lanhu_say_list查看留言列表
lanhu_say_detail查看留言详情
lanhu_say_edit编辑留言
lanhu_say_delete删除留言
lanhu_get_members查看协作者

How to install the Lanhu MCP MCP server

**Cursor / Windsurf 等其他客户端配置示例:**
```json
{
  "mcpServers": {
    "lanhu": {
      "url": "http://localhost:8000/mcp?role=Developer&name=YourName"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
LANHU_USER_NAMEConfiguration value read at startup.Optional
LANHU_USER_ROLEConfiguration value read at startup.Optional
LANHU_COOKIEConfiguration value read at startup.Optional
FEISHU_WEBHOOK_URLEndpoint or connection string the server talks to.Yes
SERVER_HOSTEndpoint or connection string the server talks to.Optional
SERVER_PORTConfiguration value read at startup.Optional
DATA_DIRFilesystem location the server is allowed to use.Optional
HTTP_TIMEOUTConfiguration value read at startup.Optional

Example prompts to try

  • Use Lanhu MCP to lanhu resolve invite link.
  • Use Lanhu MCP to lanhu get pages.
  • Use Lanhu MCP to lanhu get ai analyze page result.

Frequently asked questions

It connects Lanhu MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (lanhu_resolve_invite_link, lanhu_get_pages, lanhu_get_ai_analyze_page_result, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Lanhu MCP directly.