Atmosphere777
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Atmosphere777What's the current weather and indoor conditions?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Atmosphere777
一个可自托管的室内外环境观测站:把和风天气、室内温湿度、MCP 工具、只读 REST API 和黑白像素风 PWA 放在同一个轻量项目里。
它包含什么
5 个 MCP 工具:实时天气、24 小时预报、7 日预报、天气预警、室内温湿度;
4 个供网页调用的只读天气 REST 端点;
1 个带 Bearer Token 的室内传感器上报端点;
响应式 PWA 前端,支持手机、桌面与低刷新墨水屏;
Docker Compose、Nginx 示例和严格的容器资源限制;
面向人类和 AI 编程助手的部署、定制与交接文档。
室内传感器是可选项。只有 VPS、没有任何温湿度硬件,也可以运行完整的室外天气、预报、预警、MCP 和 PWA。把 frontend/config.js 中的 indoorEnabled 改为 false,房间模块就会干净地隐藏。
Related MCP server: open-meteo-mcp
架构
QWeather ──> atmosphere-mcp ──> /mcp ──> Claude / Codex / other agents
└──> weather-api ─────> /weather/* ─┐
BLE / other sensor ─> sensor-api ─> /sensor ├──> PWA frontend
└──> indoor_climate_now完整说明见 docs/architecture.md。
只在家庭局域网使用也没问题,见 docs/lan-deployment.md。
快速开始
1. 准备配置
cp .env.example .env
cp sensor.env.example sensor.env
mkdir -p keys在和风天气开发控制台创建 JWT 凭据,把 Ed25519 私钥保存为:
keys/qweather-ed25519-private.pem然后填写 .env 中的 API Host、Project ID、Key ID 和默认位置。真实配置和私钥已被 .gitignore 排除,绝不要提交。
2. 启动服务
docker compose up -d --build
docker compose ps本机端口:
服务 | 地址 |
MCP |
|
室内传感器 |
|
天气 REST |
|
3. 上报一条室内数据
curl -X POST http://127.0.0.1:8002/sensor/update \
-H "Authorization: Bearer YOUR_SENSOR_INGEST_TOKEN" \
-H "Content-Type: application/json" \
-d '{"temperature":24.6,"humidity":46.0}'也可以使用 examples/push_sensor.py 从任意脚本或蓝牙采集程序上报。
没有传感器时跳过本步骤,并把 frontend/config.js 的 indoorEnabled 设为 false。indoor_climate_now 会返回 freshness: "unavailable",不会令整个 MCP 服务失败。
4. 发布网页与 HTTPS
把 frontend/ 中的静态文件放到 /var/www/atmosphere,将 frontend/atmosphere.nginx.conf 里的 atmosphere.example.com 替换成自己的域名,再申请证书并启用站点。完整步骤见 docs/deployment.md。
MCP 客户端配置
部署 HTTPS 后,把下面的 URL 添加到支持 Streamable HTTP 的 MCP 客户端:
https://atmosphere.example.com/mcp工具名称是稳定接口,不应在普通定制中修改:
outdoor_weather_nowoutdoor_weather_hourlyoutdoor_weather_dailyweather_alertsindoor_climate_now
给 AI 编程助手
让 AI 先读取仓库根目录的 AGENTS.md,再读取 docs/ai-handoff.md。它们明确写出了秘密边界、允许修改范围、部署顺序和验收清单。
安全边界
和风私钥只挂载到后端容器,前端永远不接触它;
传感器写入使用独立 Bearer Token;读取接口默认公开,若数据敏感请在 Nginx 增加认证;
MCP、REST 和传感器服务仅监听
127.0.0.1,由反向代理暴露必要路由;容器使用只读文件系统、移除 Linux capabilities,并设置 CPU/内存限制。
许可证
MIT。可以使用、修改、再发布,也欢迎保留出处。
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
MCP server for weather with reasoning — umbrella advice, outdoor checks, city comparisons.
An MCP server for weather information by @kulybaba
An MCP server for weather information by @kulybaba
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP Server for global weather, forecasts, air quality, and climate data using Open-Meteo, no API key required.17 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceMCP server for Open-Meteo free weather APIs, offering 16 tools for forecast, historical, air quality, marine, flood, ensemble, climate, seasonal, and scheduled data collection with no API key required.68 npmMIT
- AlicenseAqualityBmaintenanceMCP server for weather forecasts via Open-Meteo (no API key needed), providing current weather, hourly, and daily forecasts with geocoding support.3MIT
- FlicenseAqualityCmaintenanceAn MCP server that provides live weather data over stdio, with tools for current conditions, 5-day forecasts, and US weather alerts.321 npm-