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。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

Lombardia Trains

作者:DenisRaimondi版本 0.1.1i★ 0i在你的电脑上运行代码仓库 ↗
注册名称io.github.DenisRaimondi/lombardia-trains

安装方法

能做什么

Live Lombardy train boards, delays, platforms, and journey planning. No API key.

作者提供的原文

  • 连接方式 在你的电脑上运行
  • 账号或密钥 无需密钥
  • 分类 其他

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度0/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度7/1230 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7/100

质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

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 Lombardia Trains。按照 https://mcp.popnx.com/i/denisraimondi-lombardia-trains.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

不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

让 AI 帮你安装

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 Lombardia Trains,按顺序:1) 2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "lombardia-trains": { "command": "dnx", "args": [ "LombardiaTrains.Mcp", "--yes" ] } } } 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 Lombardia Trains 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。

  1. 打开电脑版 Claude 应用的设置文件

    SettingsDeveloperEdit Config

  2. 粘贴这些设置并保存文件

    {
      "mcpServers": {
        "lombardia-trains": {
          "command": "dnx",
          "args": [
            "LombardiaTrains.Mcp",
            "--yes"
          ]
        }
      }
    }
  3. 退出 Claude 再重新打开

  4. 试一试

    用 Lombardia Trains 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 Lombardia Trains,或回答中出现 Lombardia Trains 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 Lombardia Trains

Lombardia Trains 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

你可以改用这些方式

A · 使用能连接 Lombardia Trains 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
  • 不需要密钥,不用安装程序
  • 不需要密钥,不用安装程序
  • 不需要密钥,不用安装程序

B · 其他 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

不需要密钥,不用安装程序

让 AI 帮你安装

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 Lombardia Trains,按顺序:1) 2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user lombardia-trains -- dnx LombardiaTrains.Mcp --yes 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 Lombardia Trains 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。

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --scope user lombardia-trains -- dnx LombardiaTrains.Mcp --yes
  3. 在 Claude Code 中输入 /mcp

    应能看到 Lombardia Trains 在列表中并显示已连接

  4. 试一试

    用 Lombardia Trains 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 Lombardia Trains,或回答中出现 Lombardia Trains 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

不需要密钥,不用安装程序

让 AI 帮你安装

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 Lombardia Trains,按顺序:1) 2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "lombardia-trains": { "command": "dnx", "args": [ "LombardiaTrains.Mcp", "--yes" ] } } } 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 Lombardia Trains 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。

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Lombardia Trains 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 Lombardia Trains,或回答中出现 Lombardia Trains 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

不需要密钥,不用安装程序

让 AI 帮你安装

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 Lombardia Trains,按顺序:1) 2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "lombardia-trains": { "type": "stdio", "command": "dnx", "args": [ "LombardiaTrains.Mcp", "--yes" ] } } } 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 Lombardia Trains 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。

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Lombardia Trains 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 Lombardia Trains,或回答中出现 Lombardia Trains 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

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Lombardia Trains 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

安装在电脑上

Claude Code

claude mcp add --scope user lombardia-trains -- dnx LombardiaTrains.Mcp --yes

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "lombardia-trains": {
      "command": "dnx",
      "args": [
        "LombardiaTrains.Mcp",
        "--yes"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "lombardia-trains": {
      "command": "dnx",
      "args": [
        "LombardiaTrains.Mcp",
        "--yes"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "lombardia-trains": {
      "type": "stdio",
      "command": "dnx",
      "args": [
        "LombardiaTrains.Mcp",
        "--yes"
      ]
    }
  }
}

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。

一览

每周下载量i
不在 npm/PyPI 上
连接方式
在你的电脑上运行
最新版本i
0.1.1
分类i
其他
发布到注册中心i
2026年8月24日
代码最后更新i
2026年9月6日
作者
DenisRaimondi
软件包
nuget: LombardiaTrains.Mcp
注册状态
活跃

哪些应用可以使用它

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

全部应用及其优缺点 →

它能做什么

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。

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20日

  • ✓ 通过

    作者与仓库一致

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

  • ✓ 通过

    仍在维护

    代码最后更新于2个月前

  • ✓ 通过

    有许可证

    使用 MIT

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    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

已公开的漏洞(OSV.dev)

未检查:只能检查标明版本的 npm 和 PyPI 包

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/denisraimondi-lombardia-trains.svg)](https://mcp.popnx.com/en/servers/denisraimondi-lombardia-trains)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 20815 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 20815 个服务器的 24% 更新
  • 基础检查结果等于或优于此分类中其他 20815 个服务器的 99%

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

Lombardia Trains 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?

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)。

它还在维护吗?

GitHub 仓库最后更新于2个月前,最新版本(0.1.1)于3个月前进入注册中心。

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。你的电脑上还需要有 .NET。

有什么可以替代它?

同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

功能相近的其他选择

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

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.

作者:koala73广泛使用★ 9.1万4天前更新

在云端运行✓ 服务方 · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

作者:openstatusHQ广泛使用★ 92762个月前更新

在云端运行✓ 服务方 · openstatus.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

作者:Klavis-AI正在增长★ 582414个月前更新

在云端运行仓库已归档✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

作者:jitsucom广泛使用★ 51364个月前更新

在云端运行✓ 服务方 · jitsu.com
与相似项目对比
本项
Lombardia Trains
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
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,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否否否否否否
基础检查3/34/44/44/41/44/4
许可证MITAGPL-3.0AGPL-3.0MITApache-2.0MIT
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

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。

Lombardia Trains MCP

An MCP server that answers questions about Lombardy trains: departure and arrival boards, live delays, platforms, stop-by-stop progress, cancellations and crowding — and plans journeys with a change, from the regional timetable Regione Lombardia publishes as open data. It reads the public ViaggiaTreno (RFI/Trenitalia) and Trenord APIs. No API key, no account, no scraping.

> is the next train to Malpensa on time?

Departures — MILANO CADORNA (S01066), 21:29 21:23 REG787 SEVESO +2' platform 9 21:26 REG387 MALPENSA AEROPORTO TERMINA -2' platform 1 21:32 REG887 SARONNO 0' platform 6

Install

dotnet tool install -g LombardiaTrains.Mcp

Then register it with your MCP client. For Claude Desktop, in claude_desktop_config.json:

{

"mcpServers": { "lombardia-trains": { "command": "lombardia-trains-mcp" } } }

For Claude Code:

claude mcp add lombardia-trains -- lombardia-trains-mcp

Tools

ToolWhat it answers
now"what time and day is it in Italy?"
search_station"what is the station code for Milano Centrale?"
get_departures"what is leaving Milano Cadorna on Saturday morning?"
get_arrivals"when does the train from Varese get in?"
find_connection"which direct trains go from Milano Cadorna to Como?"
find_journey"how do I get from Castellanza to Como Lago on Monday morning?"
get_train"where is train 4307 right now, and how late is it?"

Station arguments take either a code (S01700) or a name (milano centrale), and times take either HH:mm for today or ISO 2026-08-29T09:00 for another day.

Three behaviours exist because the caller is a language model rather than a person, and each of them prevents a confident wrong answer:

  • `now` exists at all because a model has no reliable idea of the date in Rome, and every relative question — "tonight", "Saturday" — needs one before any other tool can be called.
  • Ambiguous names are never resolved silently. "Milano" matches twenty-six stations, and many towns have both a national station and a separate "Nord" one served by entirely different trains. The tools return the list and ask, rather than picking the first and sounding certain.
  • Unknown places say where coverage ends. Asking for Lugano returns an explanation of what the service covers, so the model can decline instead of inventing a train to Switzerland.

find_connection finds direct trains only, and says so. It reads live departure boards and each candidate train's stop list rather than a timetable, so it carries delays and platforms but cannot compose a change.

find_journey composes one. It plans from the regional timetable, falls back to Swiss open data for anywhere that timetable does not reach, and returns scheduled times with no delays in them — the two tools answer different halves of the same question and are meant to be used together.

Journeys are ranked by arrival, not departure. Someone asking how to get somewhere wants to be there soonest, and ranking by departure puts a train that leaves four minutes earlier and arrives forty minutes later at the top of the list.

Only one change is searched for. Two multiply both the search space and the ways to be quietly wrong, and on this network almost everything worth reaching is reachable with one — so the limit is stated rather than hidden behind an incomplete search.

The part worth reading

Both upstream APIs are public, undocumented and a little hostile. Most of the work in this repository is not calling them, it is surviving them. Each of the following is enforced in code and covered by a test.

Trenord wants two headers, not one

Trenord answers 403 Forbidden unless the request carries both an Accept header and a User-Agent:

RequestResult
no headers403
Accept: */* only403
User-Agent only403
both200

This is easy to get half right. Probing the endpoint with curl or Python suggests that Accept alone is enough, because both send a User-Agent of their own without being asked. .NET's HttpClient sends neither header unless told to — so a client that sets only Accept keeps getting 403, and finds out in production rather than on the machine where the call was first tried by hand.

That is the whole reason TrenordClient sets both in its constructor.

Optional fields are absent, not null

average_crowding, average_crowding_label, suppression_type and alerts do not appear in the Trenord payload at all when there is nothing to report. They are not null: the properties are missing.

Verified against five regular services (S5, S11, RE_5, R27): none of them carried any of the four. Code that assumes these fields exist therefore works on the trains that have problems and crashes on the ones that do not, which is the worst possible way round.

Timestamps come in three different shapes
  • Trenord dep_time / arr_time — local time, "HH:MM:SS". Safe to display.
  • Trenord dep_date_time / arr_date_time — ISO 8601 in UTC, with the Z. Convenient for date arithmetic, wrong if you show it as it is.
  • ViaggiaTreno — epoch milliseconds, always to be converted declaring Europe/Rome explicitly. Converting with the machine's local time gives the right answer on an Italian laptop and the wrong one on a UTC server.
ViaggiaTreno wants JavaScript's idea of a date

Board endpoints take the timestamp spelled the way Date.toString() spells it:

Mon Aug 10 2026 20:20:00 GMT+0200

Day and month names must be English. They are built from fixed arrays on purpose: formatting them through the machine's culture produces lun ago on an Italian system and the endpoint silently returns nothing.

Two more small ones
  • ViaggiaTreno's train lookup answers with plain text, not JSON — one line per run, with the fields needed by the live-progress endpoint after a |.
  • It also returns an empty body instead of an empty array when there is nothing to report, which makes a naive deserializer throw.
  • train_operator uses $:$ as its separator, literally.
Read the operator's file, not the portal's copy of it

Trenord publishes this timetable as a GTFS zip under CC0, and the same portal also serves it exploded into one queryable table per file. The tables look like the easier option — paged JSON, filterable, no zip to unpack — and they are a lossy copy. Measured against the file they are built from:

the zipthe tables
stop times90,55368,952
trips8,4706,265

A quarter of the timetable does not survive the import, and it does not go missing tidily: trips arrive truncated. Train 11827 runs Varese to Milano and on; in the tables it stops at Porta Garibaldi, so everything reachable by staying on it is invisible, and Varese to Bergamo came back an hour worse than the published answer. Reading the zip, it matches to the minute.

Three more things the import breaks, each of which costs real code to work around and none of which is wrong in the file:

  • Times land inside a placeholder date. GTFS writes a service past midnight as 24:05; a datetime cannot hold that, so it becomes 00:05 and the train arrives eighteen hours before it left. The file says 24:05.
  • Service ids are rewritten with a hash and no longer match the ones in calendar_dates, so the two files cannot be joined on the key they share. Cutting both back to the number before the hyphen makes them join again — and merges every seasonal variant of a train into one, leaving nothing to say which of them runs today. In the file, trips and calendar_dates both write 1001A-2025-12-14-2026-12-12. The join is exact and the ambiguity does not exist.
  • `trip_short_name` is dropped entirely. That is the train number — the one field that connects a planned leg to the live data.

The decimal point also goes missing from coordinates, and route_type differs: the tables call R23 and RE4 trains, the file calls them buses.

Ask the operator, then say so

The file is not the operator's own answer either, and it is worth being precise about the size of the gap. Checked against 28 journeys published by the operator's own planner, on the same day:

  • Milano Centrale to Bergamo: the feed times train 2217 at 48 minutes, the operator at 52.
  • Pavia to Mortara: train 10668 arrives 09:28 in the feed, 09:23 in the answer.
  • Lecco to Bergamo: train 10719 reaches Ponte S.Pietro at 08:52 in the feed and its connecting coach leaves at 08:51 — a change the feed itself makes impossible and the operator has working with five minutes to spare.

The operator runs HAFAS over an internal timetable with real-time folded in. A GTFS export of it is not it. But the live sources here are the operator's own, and the file carries the train number, so every leg can simply be looked up and asked. Where it answers, its times are the ones shown, the timetable's are kept in brackets beside them, and platforms, delays and cancellations come with them.

Against those same 28 journeys that takes exact agreement from 22 to 27.

The one that remains is the shape of what this cannot do. Lecco to Bergamo is still answered with the 09:01 coach rather than the 08:51 one, because the feed said the train arrived at 08:52 and the search discarded that connection before anything was checked. Correcting after the planning fixes what is shown; it does not recover what the wrong data excluded. Live data is asked for today and tomorrow only — beyond that there is nothing live to ask.

The planner behind the border does not know it is lost

Where the regional timetable does not reach, journeys fall back to Swiss open data. That planner covers Switzerland and reaches into Italy near the border. It does not cover the rest of the country — and asked about it, it does not say so. It matches the name against its own index and answers about whatever it found.

Asked to plan Milano Centrale to Roma Termini, it returned a confident, correctly formatted, two-hour itinerary to *LaCLINIQUE of Switzerland, Locarno, Via Bossi 2*. Roma Termini to Napoli Centrale became a four-change, four-hour journey ending at a street address in Lucens, canton Vaud.

Nationality is not the test that catches this: the Swiss index holds Zurich, and ViaggiaTreno holds Zurich Altstetten, so "are both stations Italian" rejects a real journey to Zurich while letting the clinic through. The test that works is whether the answer is about the places that were asked for — one substantial word in common, accents folded, so *Zurich* matches *Zürich HB* and *Roma Termini* matches nothing in Locarno. An answer that fails it is discarded rather than passed on, and the reply names the live tools, which do work for those stations.

How accurate this is, and how that was measured

Twenty-eight journeys published by the operator's own planner were compared against what this returns — same day, same times, thirteen routes across the region — and where the two disagreed, the live train data was asked to settle it. Twenty-seven of the twenty-eight match to the minute.

That is a measurement of two things at once, and they are worth separating. The routing was never really the hard part on a network this size: what the number mostly measures is how faithfully open timetable data reproduces the timetable the operator actually runs. The answer is: closely, and not exactly.

An open feed is an export. The operator plans on an internal system with real-time folded into it and publishes a snapshot of that system as GTFS, on its own schedule. A snapshot trails the thing it is a snapshot of — that is what a snapshot is, not a defect of

只显示了开头部分;其余内容请在仓库中阅读