Mu
News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint.
Check if a flight connection is comfortable, tight or risky, with cited airport data.
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 24/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 36/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 53 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Open Transfer Times。按照 https://mcp.popnx.com/i/joelynli0110-open-transfer-times.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月14日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Open Transfer Times,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "open-transfer-times": { "command": "npx", "args": [ "-y", "open-transfer-times-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Open Transfer Times 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
SettingsDeveloperEdit Config
{
"mcpServers": {
"open-transfer-times": {
"command": "npx",
"args": [
"-y",
"open-transfer-times-mcp"
]
}
}
}用 Open Transfer Times 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Open Transfer Times,或回答中出现 Open Transfer Times 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Open Transfer Times
Open Transfer Times 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Open Transfer Times 的应用
B · 旅行、地图与天气 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Open Transfer Times,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user open-transfer-times -- npx -y open-transfer-times-mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Open Transfer Times 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user open-transfer-times -- npx -y open-transfer-times-mcp应能看到 Open Transfer Times 在列表中并显示已连接
用 Open Transfer Times 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Open Transfer Times,或回答中出现 Open Transfer Times 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Open Transfer Times,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "open-transfer-times": { "command": "npx", "args": [ "-y", "open-transfer-times-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Open Transfer Times 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Open Transfer Times 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Open Transfer Times,或回答中出现 Open Transfer Times 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Open Transfer Times,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "open-transfer-times": { "type": "stdio", "command": "npx", "args": [ "-y", "open-transfer-times-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Open Transfer Times 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Open Transfer Times 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Open Transfer Times,或回答中出现 Open Transfer Times 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --scope user open-transfer-times -- npx -y open-transfer-times-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"open-transfer-times": {
"command": "npx",
"args": [
"-y",
"open-transfer-times-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"open-transfer-times": {
"command": "npx",
"args": [
"-y",
"open-transfer-times-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"open-transfer-times": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"open-transfer-times-mcp"
]
}
}
}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。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
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19日
注册名称已通过 GitHub 账户 joelynli0110 验证,该账户拥有此仓库
代码最后更新于前天
使用 MIT
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
OSV.dev 中没有 open-transfer-times-mcp@0.4.0 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月15日
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/joelynli0110-open-transfer-times)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
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 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。
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 仓库最后更新于前天,最新版本(0.4.0)于5天前进入注册中心。
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 Node.js。
同一分类中有:Mu, Award Travel Finder, Killbottleneck, Whimsical, HasData Google Maps
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ 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
News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint.
Search award flight availability and points pricing across 27 airlines and 23 loyalty programs.
Free-to-self-host goal and process maps for humans and AI agents, with REST API and MCP.
Create and edit flowcharts, mind maps, wireframes, and docs in Whimsical, or search your workspace.
Google Maps places, reviews, contributor history, photos and posts as JSON. No Google Cloud.
| 本项 Open Transfer Times | Mu | Award Travel Finder | Killbottleneck | Whimsical | HasData Google Maps | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 需要安装在电脑上 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 是 | 否 | 是 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 是 | 否 |
| 基础检查 | 3/3 | 4/4 | 3/3 | 3/3 | 4/4 | 5/5 |
| 许可证 | MIT | AGPL-3.0 | MIT | MIT | MIT | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
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。
An MCP server that lets AI agents check whether a flight connection is realistic before recommending or booking it.
Flight-search tools return itineraries; they do not say whether a 50-minute layover in Frankfurt is enough. This server answers that with a deterministic, explainable assessment from the open-transfer-times engine, and it returns the cited airport facts behind every estimate so the agent can show its sources.
Runs locally over stdio. No API keys, no network calls.
All tools are read-only.
| Tool | What it does |
|---|---|
check_connection | Assess one connection: a decision (recommend / caution / insufficient_data / avoid), the rating (comfortable → risky), a confidence level with reasons, the real layover, each transfer step counted with its minutes, the margin, ticket-protection exposure, and the connection airport's cited facts. |
compare_connections | Assess 2–20 itineraries (e.g. flight-search results) and rank them: by decision, then rating, then ticket protection (one ticket → unknown → self-transfer), then confidence, then margin. A connection with missing data never outranks a usable one. Pass your own id per option to map results back. |
get_airport_profile | An airport's transfer allowances, whether each is heuristic or sourced, and its cited facts with official links. |
list_airports | Airports with their own profile and how well each is sourced. |
check_connection input| Field | Required | Example | Notes |
|---|---|---|---|
from, via, to | yes | BER, LHR, PVG | IATA codes; case-insensitive. |
arrival_time | one of | 2026-09-20T10:00 | First flight's arrival, local time at via; a UTC offset (+02:00) is optional. Without a date, give clock times (14:05) for both: the layover is the clock difference, the next day if the departure is earlier. |
departure_time | one of | 2026-09-20T11:30 | Second flight's departure, local time at via. |
layover_minutes | one of | 90 | Use instead of the two times when only the layover length is known. |
ticket | no | protected | protected (one booking), separate (self-transfer), unknown (default). |
arrival_terminal, departure_terminal | no | 2, 5 | A terminal change is detected when both are given and differ. |
terminal_change | no | true | true: a change is known; false: known not to change. Omit if unknown: a possible terminal change then makes the margin a range. |
baggage_recheck | no | false | true: bags must be collected and checked in again. false: hand luggage only, or checked through. Omit only if unknown; on separate tickets the result then shows whether it matters. |
inbound_airline, outbound_airline | no | LH, LH | IATA codes of the airlines operating each flight. Decide whether an airline's minimum connection time applies; omit if unknown. |
Give either both times or layover_minutes. If both are given they must agree.
Example result text:
BER–LHR–PVG: CAUTION — The terminals are not known, and a terminal change would leave little or no margin; ask for the terminals.
Rating: REASONABLE — A practical connection on one ticket. Confidence: MEDIUM — The terminals are not known; a terminal change would make this connection tight or risky. With a terminal change (25 min) the margin would be 10 min (tight). The transfer-step durations are rule-of-thumb estimates, not sourced figures. Layover 90 min, transfer steps 55 min, margin 10 to 35 min (tight if every possible step applies). Steps counted: Move through airport 40 min (heuristic); Allow for another security check 15 min (heuristic). No other steps were counted. Possible step not counted: Change terminals 25 min (terminals not given). Give the margin as a range and ask for the missing detail if it matters. Factors: Transfer through London Heathrow; Additional security screening may apply; Moderate transfer margin. Ticket: Protected itinerary. MCT: no published minimum connection time in this data. This is a structural estimate, not proof that an airline would sell this connection. Data: London Heathrow profile (partial, 3 cited facts). Comparing several options? Send them together to compare_connections, which ranks them. Airport facts are context, not extra steps. Apply a fact only where its scope matches this trip:
On separate tickets with bags not stated, where a re-check would matter:
BER–IST–PVG: INSUFFICIENT DATA — The terminals are not known; a terminal change would make this connection tight or risky. With a terminal change (10 min) the margin would be 20 min (tight). Separate tickets, and it is not known whether bags must be collected and checked in again; a re-check would make this connection tight or risky. With a bag re-check the margin would be -15 min (risky). The result cannot be relied on.
Do not call this connection safe, fine or comfortable. Tell the user the estimate is unreliable, why, and what would settle it. Confidence: LOW, for the reasons above. Rough estimate only: layover 75 min, generic transfer steps 45 min, plus possibly 10 min (change terminals) and 45 min (collect bags and check in again). No margin is given because the data cannot support one. Steps counted: Move through airport 35 min (heuristic); Allow for another security check 10 min (heuristic). No other steps were counted. Ticket: separate tickets (self-transfer). Tell the user: if the first flight is late and the connection is missed, the second airline does not have to rebook or refund. ... Bags: not stated. If they must be collected and checked in again, the margin is -15 min (risky). Ask the user.
compare_connections explains each option that is not recommended ("Why: …"). With insufficient_data the text leaves out the rating entirely: in the agent evaluation, agents repeated "comfortable" and "healthy margin" as reassurance even when the decision said the rating could not be relied on. Since 0.2.4 it also gives no margin there, only the counted and possible step durations: a large rough margin was read as "comfortable". All numbers stay in structuredContent.mct is kept apart from the structural rating. status is none_published, not_applicable, meets_published or below_published; applicability says whether the relevant MCT applies, is unknown (e.g. operating airlines not given) or does_not_apply. Below an MCT that applies is avoid; below one that may apply is never treated as a pass.decision is the field to act on. insufficient_data means key information is missing (the confidence reasons say what): ask the user rather than recommending the connection.steps always adds up to transfer_process_minutes. Facts are listed with their scope (for example "Air France connections at Paris airports") so the agent does not apply them to the wrong trip.wall_clock_layover_minutes shows what the clocks say.The server sends usage instructions when a client connects (MCP instructions): call a tool first with what the user gave, pass layover_minutes instead of inventing times, ask only when the airport or the duration is missing, use compare_connections for comparisons, explain only the counted steps, report the decision, ask about bags on separate tickets after giving the result, and respect fact scopes (scoped facts are shown as "(Only for: …)"). Each rule addresses a failure seen when testing agents; see eval.
The same data is returned as structuredContent matching the tool's output schema.
Requires Node.js 20+.
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": { "open-transfer-times": { "command": "npx", "args": ["-y", "open-transfer-times-mcp"] } } }
Claude Code:
claude mcp add open-transfer-times -- npx -y open-transfer-times-mcp
From a clone of this repository (before the package is published):
{
"mcpServers": { "open-transfer-times": { "command": "node", "args": ["/absolute/path/to/open-transfer-times/packages/mcp/src/cli.js"] } } }
Run npm install at the repository root first.
Pair it with any MCP server that searches flights. Ask the agent something like "Find flights from Berlin to Shanghai on 20 September and rank the one-stop options by how safe the connection is" — the agent searches with one server and passes the results to compare_connections.
coverage: "baseline".Agents mostly read the text result, not structuredContent, and they repeat it to the user. Text and data changes were measured with the agent evaluation (0.2.1 to 0.4.0); these rules come from what moved the numbers. Check them before changing any result text.
TIGHT or COMFORTABLE, connections with missing data were called fine.insufficient_data or avoid, the text has no rating word ("comfortable", "healthy margin") and no margin. Twice a reassuring word slipped back in (the rating line in 0.2.0, the margin range in 0.2.3), and both times agents repeated it as reassurance. Removing it lifted low-confidence questions from 7% to 60% (0.2.1) and back from 33% to 60% (0.2.4).structuredContent.summarizeCall in eval/src/judge.js). Otherwise correct answers that cite it are graded as invented, as happened with possible_steps and worst_case in 0.2.3.Before releasing a text change: run the evaluation with the same agent, judge and --repeat 3, compare against the last release, and read the failed answers (npm run eval:failures -- ) rather than only the totals.
npm install # at the repository root
node packages/mcp/test/server.test.js npx @modelcontextprotocol/inspector node packages/mcp/src/cli.js # interactive testing