{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ygywbuqjhchj","handle":"power-ai-weather-mcp","url":"https://wellknown.network/agents/power-ai-weather-mcp","links":{"self":"https://wellknown.network/agents/power-ai-weather-mcp/record.json","html":"https://wellknown.network/agents/power-ai-weather-mcp","markdown":"https://wellknown.network/agents/power-ai-weather-mcp/record.md","api":"https://wellknown.network/api/v1/agents/power-ai-weather-mcp","status":"https://wellknown.network/api/v1/agents/power-ai-weather-mcp/status","claim":"https://wellknown.network/agents/power-ai-weather-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/power-ai-weather-mcp/claim.json","badge":"https://wellknown.network/agents/power-ai-weather-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:power-ai-weather-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"power-ai-weather-mcp","summary":"用以访问基于位置的天气数据，包括实况天气、逐小时预报、空气质量AQI，灾害预警、分钟级降水、生活建议、台风等天气数据服务","description":"# MCP Weather Service (Internal Use Only)\n\n基于 Model Context Protocol (MCP)的天气服务实现（仅限内部使用）\n\n## 功能特性\n\n- 实时天气查询\n- 天气预报（小时级和天级）\n- 空气质量查询\n- 生活指数建议\n- 日出日落时间\n- 气象灾害预警\n- 台风信息\n- 降水预报\n\n## MCP 使用\n\n### 安装 uv\n\nuv 是一款高性能的 python 环境管理工具，可以参考[官方教程](https://github.com/astral-sh/uv)安装并熟悉使用。\n\n### MCP 配置\n\n首先配置环境变量 UV_INDEX、WEATHER_ENDPOINT、APP_ID、APP_SECRET：\n\n```bash\nexport UV_INDEX=xxxx\nexport WEATHER_ENDPOINT=xxxx\nexport APP_ID=xxxx\nexport APP_SECRET=xxxx\n```\n\n然后，使用 uvx 启动 MCP 服务，服务将通过 streamable-http 协议在 http://localhost:8000/mcp 启动。\n\n```\nuvx power-ai-weather-mcp\n```\n\n## 数据结构说明\n\n服务返回的数据使用了以字段描述为键（key）的字典结构，这样能更直观地理解返回数据的含义。例如：\n\n```json\n{\n  \"天气状况\": \"晴\",\n  \"温度\": 25.6,\n  \"体感温度\": 24.8,\n  \"相对湿度\": 45\n}\n```\n\n而不是传统的以字段名为键的结构：\n\n```json\n{\n  \"text\": \"晴\",\n  \"temperature\": 25.6,\n  \"feels_like\": 24.8,\n  \"humidity\": 45\n}\n```\n\n## 许可证\n\nMIT License","publisher":null,"homepage":null,"repository":null,"version":"0.5.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:power-ai-weather-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.weather","name":"Weather","confidence":1,"provenance":"derived"}],"categories":["data"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"power-ai-weather-mcp","registry":"pypi","observedAt":"2026-09-10T10:25:32.787Z","publishedAt":"2025-05-20T09:36:17.796051Z","latestVersion":"0.5.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"power-ai-weather-mcp","url":"https://pypi.org/project/power-ai-weather-mcp/","firstSeenAt":"2026-09-10T10:23:40.497Z","fetchedAt":"2026-09-10T10:23:40.497Z","normalizedAt":"2026-09-10T10:23:40.497Z"}]},"firstSeenAt":"2026-09-10T10:23:40.497Z","updatedAt":"2026-09-10T10:25:32.787Z"}