# Remote Vegas

> Remote work spots in Las Vegas: cafés, lobbies, libraries with Wi-Fi, outlets, noise and hours.

- name: vegas.remote/remote-vegas
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 100/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/vegas.remote%2Fremote-vegas
- tools: https://api.protogrid.dev/v1/servers/vegas.remote%2Fremote-vegas/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "remote-vegas": {
      "type": "http",
      "url": "https://remote.vegas/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-10d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 100/100 (strong)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 3600000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 10 of 10 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,336 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name
- pass `stability.new_links`: no tool change named a new site

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 10, about 2,336 tokens to load them all
- tool set hash: a66e5a496c088f339bba59944b748d58
- badge: [![protogrid quality](https://protogrid.dev/badge/vegas.remote/remote-vegas.svg)](https://protogrid.dev/servers/vegas.remote/remote-vegas)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://remote.vegas/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (10)

- `add_media_link`: Partner agents only (agent token required). Attach a PUBLIC Instagram post/reel, TikTok, YouTube video/Short, X or Threads post that shows a spot's work area, credited to its creator. Stored as the platform's official embed (never downloaded or rehosted) and moderated before it shows.
- `ask`: NLWeb-style natural-language query over Remote Vegas. Use it for open questions that don't map cleanly to filters (e.g. "somewhere with a view to work on a Sunday morning"). Returns schema.org places (CafeOrCoffeeShop, Library, Hotel…) with reasons and URLs to cite; mode "summarize" adds a one-line summary.
- `check_in`: Partner agents only: needs a Remote Vegas agent token in the HTTP Authorization header; without one it returns an error. Use only to report conditions the user observed IN PERSON at a spot today (workability 1-5, Wi-Fi, outlets, noise…). Queued for human moderation before it counts. Never invent or infer values.
- `get_spot`: Use this after search_spots/recommend_spot (or when the user names a specific place) to get everything about ONE spot by slug: address, structured opening hours, Wi-Fi/outlets/noise/calls with the evidence behind each, best time to go, access tips (parking, purchase rules), approved community check-ins, credited creator posts, and links to the venue, Google Maps and Yelp.
- `get_zone`: Use this when the user wants ALL the work spots in one area (e.g. "everything in the Arts District"). Returns the zone and a compact list of its spots with slugs and urls.
- `list_zones`: Use this to learn which zone names/slugs exist (quadrants, named areas such as the Strip, Downtown, Arts District, Chinatown, Summerlin, Henderson, and landmark waypoints like UNLV or the airport), with aliases and spot counts. Call it when the user's area is ambiguous or before passing a zone to other tools.
- `recommend_spot`: Use this FIRST when the user asks where to work, study or take calls in Las Vegas/Henderson/Summerlin (e.g. "quiet café with outlets near the Strip, open late"). Returns the top spots for that need, ranked by a deterministic score over Remote Vegas's hand-checked data, with a short reason for each pick. Understands quiet/focus, calls, outlets, Wi-Fi, open late/now, free, coffee vs hotel lobby vs library, and zone names written in the text. Not for places outside the Las Vegas valley.
- `search_spots`: Use this to list or filter Las Vegas work spots by explicit criteria (zone, category, Wi-Fi, outlets, quiet, calls, open now / at a time, near a point) or by name/keyword. Returns compact rows: name, category, area, hours, Wi-Fi/outlets/noise/calls, and the spot's slug and url. For "what's best for me" questions prefer recommend_spot; for one place's full details call get_spot with the slug.
- `suggest_spot`: Partner agents only (agent token required). Use when the user names a Las Vegas place that is good for laptop work and search_spots does not find it. A human reviews every suggestion.
- `update_spot_facts`: Partner agents only (agent token required). Correct first-hand facts for one spot: hours (e.g. "Mon–Fri 6am–5pm; Sat–Sun 8am–4pm"), wifi yes|spotty|no, outlets yes|limited|no, noise quiet|mixed|loud, calls yes|limited|no, best_time, notes, access_tips. Trusted tokens apply immediately, others are queued; every edit is audited with before/after. Never copy facts from Yelp or Google.