cityvistion-mcp
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
cityvistion-mcp
mcp-name: com.cgajs/cityvistion-mcp
一套 MCP server 打通三个云端服务,让任何支持 MCP 的大模型客户端(Claude Code、codex、Gemini CLI、Kimi Code、Qwen Code、GLM Coding、Cherry Studio、Cline、Cursor、MiniMax Agent…)直接完成「一句话 → CGA 规则 → 三维模型」全链路。
NL2CGA:自然语言生成 CGA 规则源码(
nl2cga_generate_cga)CGA.js:CGA 规则在线编译为三维模型 GLB(
cgajs_compile_cga)CityEngine:官方引擎解析、一句话直接出模、官方案例库查询(
cityengine_*,其中inspect_cga/list_demos/get_demo免 key)
安装
pip install cityvistion-mcp
# 或 uvx cityvistion-mcp(免安装直接跑)Related MCP server: Ollama MCP Server
API Key
服务 | 环境变量 | 签发地址 |
CGA.js |
| |
NL2CGA |
| https://www.nl2cga.com 「我的 Key」 |
CityEngine |
| https://www.cityengine.cn 用户中心「插件 Key」 |
统一 key |
| 单服务未配专属 key 时回退尝试 |
客户端配置
Claude Code(.mcp.json 或 claude mcp add):
{
"mcpServers": {
"cityvistion": {
"command": "uvx",
"args": ["cityvistion-mcp"],
"env": {
"CGAJS_API_KEY": "<你的key>",
"NL2CGA_API_KEY": "<你的key>",
"CITYENGINE_API_KEY": "<你的key>"
}
}
}
}codex CLI(~/.codex/config.toml):
[mcp_servers.cityvistion]
command = "uvx"
args = ["cityvistion-mcp"]
env = { CGAJS_API_KEY = "<你的key>", NL2CGA_API_KEY = "<你的key>", CITYENGINE_API_KEY = "<你的key>" }Gemini CLI(~/.gemini/settings.json)、Kimi Code(~/.kimi/config.toml)、Qwen Code、GLM Coding:同上结构,详见 https://www.cgajs.com/ai-access.html
托管模式(免本地安装):https://mcp.cgajs.com/mcp(streamable-http),在客户端填 URL,key 用请求头 x-cgajs-key / x-nl2cga-key / x-cityengine-key 或 Authorization: Bearer <统一key> 传递。
典型用法(对模型说)
用 nl2cga 生成「两层坡屋顶小屋」的 CGA,再用 cgajs 编译成模型,告诉我顶点数和文件路径。
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to inspect and modify maps and scenes open in a locally running desktop GIS session through natural language, exposing 38 fixed tools for session and layer queries, fields, selection, visibility and renaming, symbology, transparency, camera and elevation, map switching, raster, layout export, whitelisted geoprocessing, and attribute editing. It routes stdio MCP calls through a Windows named pipe to a C# add-in, with no network ports and no arbitrary code execution.MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible applications to interact with local and cloud-hosted LLM models for model management, text generation, chat, embeddings, and web search/fetch.817 npmAGPL 3.0
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible applications to manage, run, chat with, and generate embeddings from local or cloud LLM models, and to perform web search and content fetching via cloud APIs.817 npmAGPL 3.0
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible applications to manage and use local or cloud LLM models through comprehensive SDK tools, including model management, text generation, chat with tool support, embeddings, and web search/fetch.817 npmAGPL 3.0