原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

AirTreks MCP

作者:Airtreks版本 1.2.8i★ –i电脑或云端
注册名称io.github.Airtreks/airtreks-mcp

安装

概览

作者提供的说明(英文原文)

Plan multi-city and RTW trips, estimate prices, and send complete trip requests to AirTreks.

PopNx MCP 的三大支柱

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。

它能帮你做什么

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。

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

你需要

  • 在云端运行无需安装任何东西,通过互联网连接
  • npm已安装 Node.js(用于 npx 命令)

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 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://mcp.airtreks.com/mcp

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "airtreks": {
      "command": "npx",
      "args": [
        "-y",
        "airtreks-mcp"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http airtreks https://mcp.airtreks.com/mcp

或者在你的电脑上运行

claude mcp add airtreks -- npx -y airtreks-mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "airtreks": {
      "url": "https://mcp.airtreks.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "airtreks": {
      "command": "npx",
      "args": [
        "-y",
        "airtreks-mcp"
      ]
    }
  }
}

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。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "airtreks": {
      "type": "http",
      "url": "https://mcp.airtreks.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "airtreks": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "airtreks-mcp"
      ]
    }
  }
}

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。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://mcp.airtreks.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

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。

它能做什么

工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • plan_route

    Lay out a multi-city trip: direction of travel, regions crossed, backtracking, where a surface sector could replace a flight, and how complex the trip is to ticket. Give it your cities. It does not choose airlines and gives no prices - use route_estimate for a price range and tri

  • trip_idea_create

    Submit the customer's trip to AirTreks as a complete, structured trip request - a human travel consultant takes over from there. Ask the traveler for everything before calling, never guess or fill in defaults: name, email, the cities in order (3-letter IATA codes), a departure da

  • route_estimate

    Get a price range for a multi-city or round-the-world trip, drawn from what AirTreks customers have actually paid on those routes. Give it the cities and it returns a per-person range in USD with how much history sits behind it. Use it when someone asks what a trip will cost and

  • fare_quote

    Get live, bookable-quality fares for one specific itinerary — actual flights, actual prices, for the dates given. Needs a departure date for every flown leg. Use this once the customer has settled on cities and dates and wants real numbers rather than a ballpark; use route_estima

  • itinerary_quote

    Price a complete multi-stop or round-the-world trip and get back several ways of ticketing it — cheapest, fastest, fewest stops — with the actual tickets each one is built from. Use this for trips that will not go on a single fare, which is most itineraries with 3+ stops; use far

  • itinerary_quote_status

    Fetch the result of an itinerary_quote using the quoteReference it returned. Call it straight away: it waits up to about 40 seconds for a quote that is still pricing, then returns the finished options, or status 'pending' if the quote needs one more call. Costs nothing and does n

  • route_validate

    Validate a multi-city flight routing for feasibility. Checks alliance carrier rules, identifies dead legs, warns about poison carriers, and estimates bookability. Use this before building an itinerary to catch routing problems early.

  • route_suggest

    Get suggested multi-stop flight routings based on regions, direction, and alliance preference. Returns up to 3 proven routing templates with bookability ratings. Great for trip planning inspiration.

  • hub_check

    Check the best connection between two airports. Identifies dead legs (routes that fail on alliance fares), suggests hub routing fixes, and shows proven carrier combinations. Essential for transpacific, kangaroo, and intra-Asia routing.

  • fare_product_match

    Recommend the best fare product type for a route — RTW, Circle Pacific, Circle Atlantic, Open Jaw, or Custom Multi-City. Considers stop count, direction, and backtracking to match the right alliance fare structure.

  • custom_route_build

    Break a complex multi-city itinerary into individually-ticketable segments with carrier recommendations. Handles routes that don't fit alliance fare rules — mixed carriers, LCCs, Gulf bridge connections, surface sectors. This is how AirTreks consultants build 90% of itineraries.

基础检查i

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7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 Airtreks 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • ✓ 通过

    端点有响应

    在 165 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 11 个工具描述,未发现针对 AI 的隐藏指令

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 18349 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 18349 个服务器的 92% 更新
  • 基础检查结果等于或优于此分类中其他 18349 个服务器的 100%

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。

常见问题

AirTreks MCP 安全吗?

它在 3 项适用的基础检查中通过了 3 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。

它需要哪些密钥或代码?

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。

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(1.2.8)于3天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, arr-mcp

替代选择

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

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211前天更新
安装

arr-mcp

作者:bardesss

One server, 40 tools, the whole media stack: *arrs, Jellyfin, Plex, Seerr, Cleanuparr, downloaders

在你的电脑上运行今天更新
安装

作者的 README

打开 README

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。

AirTreks MCP Server

The complex-itinerary tool for AI agents. Multi-stop, round-the-world, open-jaw, surface segments - the trips that standard flight search can't handle. When your user asks for 3+ stops across continents, this server answers with routing analysis built on real AirTreks fare-construction data: 60+ carriers, 53 known dead legs, bookability rates measured from 1,400+ real fare attempts, and 20 proven routing templates from actual bookings.

Live endpoint: https://mcp.airtreks.com/mcp - free, no API key, 100 requests/day.

Now with real prices: a historical range for any route in under a second, live fares for a specific itinerary, and a full multi-stop trip priced across several tickets — the same trip can vary three-fold depending on how it is ticketed, and that is the part no other flight tool will tell you.

30-second setup

Claude Desktop

Settings → Connectors → Add custom connector → paste https://mcp.airtreks.com/mcp.

Claude Code
claude mcp add --transport http airtreks https://mcp.airtreks.com/mcp
Cursor

Add to .cursor/mcp.json (or Cursor Settings → MCP → Add new server):

{

"mcpServers": { "airtreks": { "url": "https://mcp.airtreks.com/mcp" } } }

No API key is needed for any tool, the consultant handoff included. A key is optional and only raises your daily limit; append it to the URL if your client cannot send custom headers, as claude.ai connectors cannot:

https://mcp.airtreks.com/mcp?key=at_your_key
ChatGPT

Settings → Apps & Connectors → enable Developer mode (Pro/Business plans) → add https://mcp.airtreks.com/mcp as a custom connector.

Any other MCP client

Same JSON shape as Cursor above (Streamable HTTP). Prefer stdio? Run it locally:

npx airtreks-mcp

Then ask your agent:

Plan a round-the-world trip: San Francisco, Tokyo, Bangkok, Singapore, Delhi, Istanbul, London, back to San Francisco.

One call, one answer: a 7-leg RTW

Your user wants six stops around the world. Google Flights gives up. One plan_route call lays the trip out, and one route_estimate call says what it costs. Neither one picks airlines: AirTreks consultants do that when they build the ticket.

{

"cities": ["SFO", "NRT", "BKK", "SIN", "DEL", "IST", "LHR", "SFO"], "budget": "mid" }

Real plan_route response, trimmed for length (the full version has notes for all 7 legs):

{

"route": "SFO -> NRT -> BKK -> SIN -> DEL -> IST -> LHR -> SFO", "totalLegs": 7, "isRoundTrip": true, "direction": "westbound", "backtracking": false, "regionsCrossed": ["americas", "asia", "europe"], "customBuild": { "strategy": "7-leg route. 1 surface sector opportunity.", "surfaceSectors": [ { "insteadOf": "BKK -> SIN (leg 3)", "suggestion": "Bangkok to Singapore through Malaysia. Train, bus, or ultra-cheap LCC. Adds Malaysia and possibly Penang, KL, Melaka.", "savings": "Saves $100-250" } ], "complexity": "moderate" } }

And route_estimate on the same cities:

{

"cabin": "economy", "currency": "USD", "estimate": { "low": 1616.43, "high": 2465.75 }, "confidence": "medium", "basis": "1,616-2,466 USD per person, from AirTreks fare history. We have history for most of this route, but not all of it." }

That is a range from past AirTreks bookings, not a quote. For a real number, trip_idea_create hands the complete trip - route, a date for every leg, passengers, cabin and the traveler's answers to our planning questions - to an AirTreks consultant who prices and books it.

Tools

All tools are free and need no API key — 100 requests/day per IP.

Routing
ToolDescription
plan_routeLay out a multi-city trip - direction, regions crossed, backtracking, surface-sector options, and how complex it is to ticket. No airline picks
route_validateValidate a multi-city routing - alliance rules, dead legs, poison carriers, bookability
route_suggestGet 3 suggested routings by region, direction, and alliance
hub_checkBest connection between two airports - dead leg detection + hub fixes
fare_product_matchMatch the right fare product (RTW, Circle Pacific/Atlantic, Open Jaw, Custom) with typical price ranges
custom_route_buildBreak a multi-city itinerary into legs with surface-sector options and how much each leg benefits from a consultant. No airline picks
Pricing
ToolDescription
route_estimatePrice range for a route from AirTreks fare history. No dates needed, answers in about a quarter of a second — the right tool when someone asks "what will this cost?" before anything is decided
fare_quoteLive fares for one specific itinerary on specific dates, priced as a single ticket
itinerary_quotePrices a whole multi-stop trip and returns several ways to ticket it — cheapest, fastest, fewest stops — with the tickets each one is built from. Takes about a minute, so it returns a reference immediately
itinerary_quote_statusFetches an itinerary_quote result by its reference, waiting up to about 40 seconds for one still pricing. Free to call again
Consultant handoff
ToolDescription
trip_idea_createHand off to an AirTreks human travel consultant - submits the trip request with the full routing analysis attached

Submits real customer contact details, so only call it with the customer's knowledge and consent. Repeat submissions of the same email + route inside 24 hours return the existing trip request rather than creating a duplicate.

Why this data is different

AirTreks has built complex multi-stop itineraries since 1987. This server exposes what that history taught us:

  • Dead legs - city pairs that look bookable but fail on alliance fares, learned from 1,400+ real fare-construction failures
  • Bookability rates by leg count - measured, not estimated (91% at 3-4 legs, 61% at 5-6, 6% at 7+)
  • Poison carriers and hub fixes - we know what airline combinations break ticketing and what to route instead
  • Proven routing templates from working with Multi-Stop and Around the World Intineraries for inviduals, families and large group

No other flight tool returns this because no other flight tool has priced these failures.

REST API (no MCP client required)

Every tool is also a plain REST endpoint - same tools, same rate limits, JSON in/out. For agent frameworks that consume REST instead of MCP:

curl -X POST https://mcp.airtreks.com/api/plan_route \

-H "Content-Type: application/json" \ -d '{"cities": ["LAX", "NRT", "BKK", "LHR", "LAX"]}'

Full OpenAPI 3.1 spec: https://mcp.airtreks.com/openapi.json

Rate limits

  • Free: 100 requests/day per IP, no key needed — every tool, trip_idea_create included
  • Registered: higher limits with an API key (X-API-Key header, or ?key= for clients that cannot set headers)

Endpoints

PathDescription
/mcpMCP protocol endpoint (Streamable HTTP)
/api/{tool}REST twin of each tool (POST, JSON body)
/openapi.jsonOpenAPI 3.1 spec for the REST surface
/healthHealth check
/registerGet an API key for a higher rate limit (POST)
/privacyPrivacy policy
/favicon.ico, /favicon.svgAirTreks mark — the icon AI directories show for this server
/Server info

License

AGPL-3.0-only

问 PopNx