timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Read-only Italian bus searches and local NeTEx rail schedules.
Skills that teach the AI this kind of work; they work alongside this one
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 0/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 12/100 |
Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Pick the AI app you use, then copy the settings.
Passed 3/3 checks · Runs on your computer
We hid some of the commands
Run on your computer: the package was not found in its registry when we checked
No install path has passed yet. See the maker’s instructions or pick another server in this category · Maker’s install instructions · Others in this category
First: which AI do you use?
Pick your app and the steps appear below.
Claude cannot connect Italian Bus and Rail Search MCP Server yet
No install path has passed yet. See the maker’s instructions or pick another server in this category
ChatGPT cannot connect Italian Bus and Rail Search MCP Server yet
No install path has passed yet. See the maker’s instructions or pick another server in this category
Claude Code cannot connect Italian Bus and Rail Search MCP Server yet
No install path has passed yet. See the maker’s instructions or pick another server in this category
Cursor cannot connect Italian Bus and Rail Search MCP Server yet
No install path has passed yet. See the maker’s instructions or pick another server in this category
VS Code cannot connect Italian Bus and Rail Search MCP Server yet
No install path has passed yet. See the maker’s instructions or pick another server in this category
No install path has passed yet. See the maker’s instructions or pick another server in this category
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
GooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026
The registry name was verified with the GitHub account Alexxanddr, which owns the repo
Code last changed 12 days ago
Uses MIT
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
No entries on OSV.dev for italian-bus-search@0.3.0
Checks only this package version, not every dependency · checked Nov 15, 2026
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/alexxanddr-italian-bus-search)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed 12 days ago, and the latest version (0.3.0) reached the registry 24 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
Search and read Empryo's documentation. Read-only, no auth, no local access.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| This one Italian Bus and Rail Search MCP Server | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install |
| Needs a key | No | No | No | No | No | No |
| Add with + in Claude | No | Yes | Yes | Yes | No | No |
| Basic checks | 3/3 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| License | MIT | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An unofficial, read-only TypeScript service for live Italian coach and train searches through HTTP and Model Context Protocol interfaces.
The project hides provider-specific station catalogs, request formats, fare structures, and multi-leg responses behind one shared application core. Italo pricing initializes an anonymous technical session and temporary planning resource; customer login, fare selection, seat reservation, and payment are excluded.
[!IMPORTANT]
This project is not affiliated with or endorsed by Itabus, Autoservizi Salemi, Autolinee Federico, MarinoBus, or FlixBus. Provider names and trademarks belong to their owners. Before enabling a live adapter, confirm that your use complies with the provider's terms, applicable law, and any required authorization. This repository does not grant data-extraction or redistribution rights.
/mcp, with backward-compatible bus tools and separate rail tools.| Provider ID | Operator | Integration | Locations | Journeys |
|---|---|---|---|---|
itabus | Itabus | Demandware endpoints | Live | Live |
salemi | Autoservizi Salemi | Albatross tenant | Live | Live |
federico | Autolinee Federico | Albatross tenant | Live | Live |
marinobus | MarinoBus | Albatross tenant | Live | Live |
flixbus | FlixBus | Global FlixBus search API | Live | Live |
Public provider behavior and limitations are documented in the bus and train API guides below.
Train stations, journeys, prices and availability come directly from Trenitalia and Italo booking APIs. No timetable download, dataset, storage volume or initialization command is required. If one operator fails, its error is reported alongside the other operator's results. ViaggiaTreno and Italo live boards/standalone status remain independent; Italo quote sessions are cleaned up best-effort.
git clone https://github.com/Alexxanddr/italian-travel-search.git
cd italian-travel-search npm install cp .env.example .env npm start
The server listens on http://127.0.0.1:3000 by default.
curl http://127.0.0.1:3000/health
curl http://127.0.0.1:3000/providers curl http://127.0.0.1:3000/train-providers curl 'http://127.0.0.1:3000/locations?query=Roma&provider=marinobus'
For journey searches, use today or a future date in Europe/Rome:
curl 'http://127.0.0.1:3000/journeys?origin=Roma&destination=Milano&date=YYYY-MM-DD&adults=1&children=0&provider=marinobus'
YYYY-MM-DD is a placeholder and must be replaced before running the command.
The dark, Italian-language Binario interface lives in frontend/ in this repository. It searches bus and train journeys through the HTTP API, with a single origin/destination/date form, progressive results, stable snapshot pagination and official booking links. It has no account, payment, AI model or direct provider/MCPHub access in the browser.
From the repository root:
npm ci
npm ci --prefix frontend npm start
npm run web:dev
The local frontend proxy defaults to the API at http://127.0.0.1:3000. Optional local configuration belongs in ignored frontend/.env.local; copy frontend/.env.example if needed. Never use browser-exposed VITE_* variables for credentials.
npm run build:all
cd frontend npx playwright install chromium cd .. npm run check:all
npm run build and npm run check retain their existing backend behavior. The frontend shares domain types and keeps its own build lockfile. The existing root Dockerfile builds both parts into one image: Node serves the UI at /, the browser API at /api/*, the existing HTTP endpoints and MCP at /mcp, all on port 3000. No NGINX or second container is needed. The npm package remains API/MCP-focused and excludes frontend assets/tooling. See the frontend guide, single-image Docker packaging, and publication review. Publishing source code does not require hosting a live website.
The published image is multiarch: linux/amd64 and linux/arm64 share the same tag, and Docker selects the matching architecture automatically.
docker build -t italian-travel-search:local .
docker run --rm -p 127.0.0.1:3000:3000 italian-travel-search:local
Without Docker, npm run build:all followed by node dist/index.js serves the same combined application. npm run web:dev remains the optional development server with live rebuilding.
| Method | Path | Purpose |
|---|---|---|
GET | /health | Process liveness |
GET | /providers | Adapter status and operational reason |
GET | /train-providers | Train operators and configured schedule/price/live capabilities |
GET | /locations | Provider location search |
GET | /journeys | Normalized one-way journey search |
GET | /train-locations | Trenitalia/Italo station search |
GET | /train-journeys | Live rail journeys, availability and nullable prices |
GET | /train-status | Standalone live status where enabled |
GET | /station-board | Live arrivals/departures where enabled |
POST | /mcp | Stateless MCP Streamable HTTP endpoint |
/locations and /journeys accept an optional provider parameter. Without it, all providers are queried independently and successful data is preserved alongside provider-scoped errors.
The complete contract is split into the Bus API and Train API, with shared behavior indexed in HTTP API.
The simplest MCP configuration runs the published package directly with npx:
{
"mcpServers": { "italian-travel-search": { "command": "npx", "args": ["-y", "italian-travel-search@latest"] } } }
Alternatively, build and start the local stdio server:
npm run build
npm run mcp:built
The existing list_providers, search_locations, and search_journeys bus tools remain compatible. Location and journey searches accept optional offset/limit; increment offset by limit until truncated is false to retrieve every page. Rail adds list_train_providers, search_train_locations, search_train_journeys, get_train_status, and get_station_board. Trenitalia and Italo price and live adapters are enabled; Italo live tools retain date-unverified semantics.
For exhaustive journey searches, start with snapshot: true and continue with only the returned searchId, offset and limit. This keeps prices, errors, order and totals identical across pages. Expired IDs require a new search. The same opt-in flow exists over HTTP; see stable pagination.
{
"mcpServers": { "italian-travel-search": { "command": "node", "args": ["/absolute/path/to/italian-travel-search/dist/mcp/stdio.js"] } } }
For a container or remote MCPHub deployment, start the HTTP process and point the client to http://italian-travel-search:3000/mcp. The container image is ghcr.io/alexxanddr/italian-travel-search:latest. No dataset initialization or persistent volume is needed.
See MCP interface for the authoritative tool contract, limits, errors, and development command.
The application has four layers:
SearchService orchestrate searches and partial results;Provider adapters implement one shared interface, so callers do not know whether a result came from Itabus Demandware or an Albatross tenant. See Architecture for modules, seams, data flow, caches, and test strategy.
npm run dev
npm run mcp npm run check
npm run check runs the complete offline test suite, TypeScript type checking, and the configured lint check. To add an operator, follow Adding a provider; do not infer a new integration from HTML alone or copy credentials into fixtures.
The default server deliberately binds to loopback and keeps rate-limit and cache state in process memory. Read Operations before placing it behind a reverse proxy or running multiple replicas.
timetableSource is retained for compatibility.Always complete and confirm a purchase on the official provider site linked by bookingUrl.
Contributions are welcome; start with CONTRIBUTING.md