hefeng-qweather-mcp-modelscope
Click on "Install 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., "@hefeng-qweather-mcp-modelscopeWhat's the weather forecast for Hangzhou?"
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.
和风天气 MCP 服务 · ModelScope 云端托管版(v1.1.1)
本仓库是 hefeng-qweather-mcp 针对 ModelScope MCP 广场云端托管(Hosted) 的适配版本,两处关键适配:
默认 stdio 入口:无参数调用
hefeng-qweather-mcp直接以 stdio 模式启动 (原版 typer 无子命令时会打印帮助并以 exit code 2 退出)HTTP 模式监听
0.0.0.0:云端容器内必须,否则平台网关无法连接; 端口优先读PORT环境变量(云平台注入),其次MCP_PORT,默认 8000
上游源码其余部分未做任何改动。
根因:为什么原版在 ModelScope 部署不起来
原版入口使用 typer.Typer(),只定义了 http / stdio 两个子命令:
app = typer.Typer()
@app.command()
def http() -> None: ...
@app.command()
def stdio() -> None: ...
def main() -> None:
app()ModelScope 平台拉起 server 时不传子命令(对照官方
modelscope-mcp-server:
argparse + --transport 默认 stdio,无参数直接运行)。
原版此时 typer 报 Missing command. 并以 exit code 2 立即退出,
MCP server 从未启动,stdio 握手永远不会发生,平台即判定部署失败。
本地复现(原版):
$ hefeng-qweather-mcp
Usage: ... [OPTIONS] COMMAND [ARGS]...
Try 'hefeng-qweather-mcp --help' for help.
╭─ Error ───────────────────────────╮
│ Missing command. │
╰──────────────────────────────────╯
EXIT CODE: 2 ← 进程直接退出,服务未启动Related MCP server: Weather MCP Server
改动内容(相对原版的唯一差异)
在 main() 前新增一个默认 callback,无子命令时自动进入 stdio 模式:
@app.callback(invoke_without_command=True)
def default(ctx: typer.Context) -> None:
"""
默认入口:不带子命令调用时以 stdio 模式启动
"""
if ctx.invoked_subcommand is None:
stdio()行为对照:
调用方式 | 原版 | 本适配版 |
| 打印帮助,exit 2 ❌ | stdio 模式启动 ✅ |
| stdio 启动 ✅ | stdio 启动 ✅(不变) |
| http 启动 ✅ | http 启动 ✅(不变) |
| 显示帮助 ✅ | 显示帮助 ✅(不变) |
已验证:无参数调用可正确完成 MCP initialize 握手并返回 serverInfo。
部署到 ModelScope
将本文件夹内容作为部署源(独立 Git 仓库 / 分支,或替换主仓库部署目录), 确保仓库根目录包含本版的
pyproject.toml(版本 1.1.1)与src/。平台创建/更新 MCP server 时,配置环境变量(必须,否则模块导入阶段 即抛
ValueError退出):HEFENG_API_HOST=你的API主机地址 # 如 devapi.qweather.com HEFENG_API_KEY=你的API KEY若平台支持自定义启动命令,任选其一均可(本版两者都兼容):
{ "command": "hefeng-qweather-mcp" } { "command": "hefeng-qweather-mcp", "args": ["stdio"] }
零代码替代方案(如不想发适配版)
若 ModelScope 后台支持配置 command/args,直接把原版启动命令配成
hefeng-qweather-mcp stdio(带子命令)即可绕过此问题,无需改任何代码。
适配版的价值在于对任意调用方式都健壮,不依赖平台配置能力。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Open-Meteo tabanlı anahtarsız hava durumu tahmin MCP sunucusu.
An MCP server for weather information by @kulybaba
An MCP server for weather information by @kulybaba
MCP server for AI dialogue using various LLM models via AceDataCloud
Related MCP Servers
FlicenseBqualityCmaintenanceProvides a Model Context Protocol server that enables large language models to query and retrieve real-time weather forecasts for cities and regions across China.1- FlicenseNot gradedqualityDmaintenanceAn MCP server integrated with the QWeather API that provides real-time weather forecasts and meteorological warnings for AI assistants. It enables users to query current conditions and disaster alerts for specific cities or coordinates.28
- AlicenseNot gradedqualityDmaintenance基于HelloAgents框架的天气查询MCP服务器,支持12个中国主要城市实时天气查询,使用wttr.in API无需密钥。MIT
- AlicenseNot gradedqualityCmaintenanceReal-time weather query MCP server supporting 12 Chinese cities (and global cities via English names) using wttr.in API, built on HelloAgents framework.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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/fengyucn/hefeng-qweather-mcp-modelscope'
If you have feedback or need assistance with the MCP directory API, please join our Discord server