Weather MCP Server
Current weather and forecast lookup as an agent tool.
作者提供的说明(英文原文)
60-tool AI travel agent: flights, hotels, visas, weather, fare watching, trip memory. No keys.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"wander-agent": {
"command": "uvx",
"args": [
"wander-agent"
]
}
}
}在终端中运行这条命令
claude mcp add wander-agent -- uvx wander-agent粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"wander-agent": {
"command": "uvx",
"args": [
"wander-agent"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"wander-agent": {
"type": "stdio",
"command": "uvx",
"args": [
"wander-agent"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 VirajMishra1 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.1)于5个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Weather MCP Server, Travel MCP Server, Enterprise MCP Gateway
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Current weather and forecast lookup as an agent tool.
Airbnb, hotel and TripAdvisor search as agent tools.
One MCP gateway bundling 30 data servers — finance, real estate, jobs, legal, news, sports and more.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
75 tools. Zero API keys. One line to install.
Ask your AI anything about travel and get real data back, not hallucinations — live flight prices, the cheap fares airlines hide, real visa rules, 16-day forecasts, and credit-card points sweet spots.
pip install wander-agent
See the launch demo · ⭐ Star this repo if it saves you a layover ✈️
Real run: asked for "every way to save money on DXB→DPS for 4" — it surfaced hidden-city, split-ticket, and nearby-airport fares for ~$8,000 group savings.
Try these the second you install — paste any of them to your AI:
- 🛫 *"Find me a flight from NYC to Tokyo the airlines don't want me to see."* → hidden-city + split-ticket fares OTAs are banned from showing you
- 🌴 *"Plan a 10-day Bali trip for 2 from Dubai in September, budget $3,000."* → flights, hotels, visa, weather, restaurants, packing list, day-by-day — one response
- 🛂 *"Which of my two passports gets me into more countries visa-free?"* → dual-passport diff with Henley rankings
- 💳 *"Turn my Amex points into the best business-class flight to Europe."* → points sweet-spot finder across transfer partners
Wander Agent is a tool plugin for AI assistants (Claude, Cursor, Windsurf, etc.) that gives the AI real travel data to work with.
Without this plugin, asking an AI "cheapest flights from New York to Tokyo in August?" gets you a made-up answer. With this plugin, the AI calls real data sources — Google Flights, Open-Meteo, US State Dept advisories, OpenStreetMap — and gives you actual prices, real forecasts, and live visa requirements.
You talk to the AI the same way you always do. The AI does the rest.
*"Plan me a 10-day trip to Bali for 2 people leaving from Dubai in September, budget $3,000"*
→ Real flights, real hotels, visa requirements, weather forecast, local restaurants, packing list, day-by-day itinerary — all in one response.
✈️ Flights
🏨 Hotels
📋 Visas & Entry
🌤️ Weather
⚠️ Safety
💰 Costs
🗺️ Planning
🍜 Food & Nightlife
🎒 On the Ground
🧠 Memory & Decisions
💳 Credit Card Points & Miles
You need Python 3.10 or newer. Check if you have it:
python3 --version
Don't have it? Download from python.org.
From PyPI (recommended):
pip install wander-agent
Or with uv — no install at all, run directly:
uvx wander-agent
Or from source:
git clone https://github.com/VirajMishra1/wander-agent.git
cd wander-agent pip install -e .
Verify it worked:
wander-agent --help
Pick the app you use:
Claude Desktop
Open this file in a text editor:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonAdd this:
{
"mcpServers": { "wander-agent": { "command": "wander-agent" } } }
Save the file, then quit and reopen Claude Desktop.
If you get an error about wander-agent not being found, find the full path first:
which wander-agent
Then use that path in the config:
{
"mcpServers": { "wander-agent": { "command": "/usr/local/bin/wander-agent" } } }
Claude Code (terminal)
claude mcp add wander-agent wander-agent
Confirm it registered:
claude mcp list
Cursor
Create or edit .cursor/mcp.json in your home directory:
{
"mcpServers": { "wander-agent": { "command": "wander-agent" } } }
Restart Cursor.
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": { "wander-agent": { "command": "wander-agent" } } }
Restart Windsurf.
Cline (VS Code extension)
Open VS Code settings, search for "Cline MCP", edit cline_mcp_settings.json:
{
"mcpServers": { "wander-agent": { "command": "wander-agent" } } }
Continue.dev
Edit .continuerc.json in your project or home directory:
{
"mcpServers": [ { "name": "wander-agent", "command": "wander-agent" } ] }
Zed
Edit ~/.config/zed/settings.json:
{
"context_servers": { "wander-agent": { "command": { "path": "wander-agent", "args": [] } } } }
Everything works without any API keys. These add richer data if you want:
| Variable | What it unlocks | Get it free at |
|---|---|---|
FOURSQUARE_API_KEY | Real ratings and price levels for restaurants/bars | foursquare.com/developers |
TICKETMASTER_API_KEY | Live event listings (concerts, sports, shows) | developer.ticketmaster.com |
Set them before starting your AI:
export FOURSQUARE_API_KEY=your_key_here
export TICKETMASTER_API_KEY=your_key_here
Or add them to y
只显示了开头部分;其余内容请在仓库中阅读