Remote Vegas

vegas.remote/remote-vegasremote.vegasstreamable-httpv1.0.0Scanned 4 hours ago

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

10 tools: 6 change things and 4 only read.

Reads private data · 0
Reads text others write · 1
Can send data out · 1
No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

6 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

10 tools

Changes things 6Creates or changes something that can be changed back.Claude Code: ask

add_media_linkPartner agents only (agent token required).Can send data outNo findings
Why it is in this group
- The name "add_media_link" says "add": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
askNLWeb-style natural-language query over Remote Vegas.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_inPartner agents only: needs a Remote Vegas agent token in the HTTP Authorization header; without one it returns an error.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
recommend_spotUse this FIRST when the user asks where to work, study or take calls in Las Vegas/Henderson/Summerlin (e.g.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
suggest_spotPartner agents only (agent token required).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
update_spot_factsPartner agents only (agent token required).No findings
Why it is in this group
- The name "update_spot_facts" says "update": a word for a change.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 4Looks things up and changes nothing.Show 4 read-only tools

get_spotUse 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/nois…Reads text others writeNo findings
Why it is in this group
- The name "get_spot" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_zoneUse this when the user wants ALL the work spots in one area (e.g.No findings
Why it is in this group
- The name "get_zone" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_zonesUse 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…No findings
Why it is in this group
- The name "list_zones" says "list": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_spotsUse 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.No findings
Why it is in this group
- The name "search_spots" says "search": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; get_spot
Can send data out1: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; add_media_link

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 4, 2026, 02:20 UTC, unchanged since Nov 4, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 6
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: not observed
RFC 9728 protected resource metadata: not observed
Authorization servers: not observed
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://remote.vegas/api/mcp: tools/list returned 10 tools to an anonymous client, including recommend_spot (write), ask (write), check_in (write), suggest_spot (write), add_media_link (write) and 1 more
What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http remote-vegas https://remote.vegas/api/mcp

claude mcp add --transport http remote-vegas https://remote.vegas/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__remote-vegas__search_spots",
      "mcp__remote-vegas__get_spot",
      "mcp__remote-vegas__list_zones",
      "mcp__remote-vegas__get_zone"
    ],
    "ask": [
      "mcp__remote-vegas__recommend_spot",
      "mcp__remote-vegas__ask",
      "mcp__remote-vegas__check_in",
      "mcp__remote-vegas__suggest_spot",
      "mcp__remote-vegas__add_media_link",
      "mcp__remote-vegas__update_spot_facts"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as remote-vegas. Review it before you use it.

Capability tags behind 2 rules

mcp__remote-vegas__get_spot untrusted-input
mcp__remote-vegas__add_media_link outbound

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/vegas.remote/remote-vegas/verify?hash=2ca2c0ff8bad6423adfc06f88d0470cdb711c556a2c78edc105f0aece3af2911" | jq -e '.changed == false'

Pinned hash 2ca2c0ff8bad, from Nov 4, 2026, 00:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/vegas.remote/remote-vegas/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/vegas.remote/remote-vegas.svg)](https://anlyon.dev/servers/vegas.remote/remote-vegas)

Source: MCP Registry. Synced Nov 4, 2026, 00:18 UTC.