Skip to content

POS.DO MCP Server

io.github.posdo-io/mcp-serverposdo-iostreamable-httpv0.1.0Scanned

Discover 356K+ restaurants in 20 countries: search, reviews, cultural context, time-based offers.

7 tools: 1 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 1 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the POS.DO MCP Server can do

The POS.DO MCP Server is published by the GitHub account posdo-io. It has 7 tools. It can create or change data (1 tool: book_flow_reservation), but cannot delete data. 6 tools only read.

2 tools bring in text other people can write (get_restaurant_details and get_restaurant_reviews).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 0.1.0.

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.

7 tools

Changes things 1Claude Code: ask
  • book_flow_reservationMake a reservation at a Flow-discounted time slot.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
    Make a reservation at a Flow-discounted time slot. Phone must be E.164 (e.g. +34911234567). To make retries safe, send the same Idempotency-Key HTTP header on retries (any UUID); replays within 24h return the original reservation. Rate limited to 5 reservations per email per day and 10 attempts per IP per minute.
Only reads 6Show 6 read-only tools
  • find_restaurants_near_landmarkFind restaurants near a famous landmark (monument, museum, park).No findings

    Why it is in this group

    • The name "find_restaurants_near_landmark" says "find": a word for reading.
    Description, as the server wrote it
    Find restaurants near a famous landmark (monument, museum, park). Returns landmark info from Wikidata + nearby restaurants sorted by walking distance. Examples: 'Sagrada Familia', 'Colosseum', 'Central Park', 'Tour Eiffel'.
  • get_cultural_context_around_restaurantGet cultural context around a restaurant: nearby monuments, museums, parks, historical sites with distance and heritage status.No findings

    Why it is in this group

    • The name "get_cultural_context_around_restaurant" says "get": a word for reading.
    Description, as the server wrote it
    Get cultural context around a restaurant: nearby monuments, museums, parks, historical sites with distance and heritage status. Powered by Wikidata.
  • get_flow_offersPOS.DO Flow time-based offers for a restaurant.No findings

    Why it is in this group

    • The name "get_flow_offers" says "get": a word for reading.
    Description, as the server wrote it
    POS.DO Flow time-based offers for a restaurant. Off-peak hours have bigger discounts. Returns time slots with discount percentages and remaining covers. Tagline: 'Tu hora, tu precio'.
  • get_restaurant_detailsGet the full profile of a restaurant by URL slug.Reads text others writeNo findings

    Why it is in this group

    • The name "get_restaurant_details" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Get the full profile of a restaurant by URL slug. Returns name, address, coordinates, rating, reviews count, phone, opening hours, photos, services, cuisine type, price level, current Flow offers, and cultural context.
  • get_restaurant_reviewsGet paginated reviews for a restaurant.Reads text others writeNo findings

    Why it is in this group

    • The name "get_restaurant_reviews" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe name "get_restaurant_reviews" says "get" and "review": it reads comments, which other people can write.
    • untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Get paginated reviews for a restaurant. Filter by star rating, sort by date or rating. Returns review text, author, rating, date, photos, language, owner response, and rating distribution.
  • search_restaurantsSearch restaurants in a specific city.No findings

    Why it is in this group

    • The name "search_restaurants" says "search": a word for reading.
    Description, as the server wrote it
    Search restaurants in a specific city. Filter by cuisine type, price range, and features like outdoor seating, WiFi, delivery. Returns up to 20 results with name, rating, cuisine, price range, address, coordinates, photo, amenities, and current Flow offers.

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 or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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 20, 2026, 19:09 UTC, unchanged since Oct 22, 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
1
Protocol version
2024-11-05
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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://pos.do/mcp: tools/list returned 7 tools to an anonymous client, including book_flow_reservation (write)

    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.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http posdo-io https://pos.do/mcp
claude mcp add --transport http posdo-io https://pos.do/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__posdo-io__search_restaurants",
      "mcp__posdo-io__get_restaurant_details",
      "mcp__posdo-io__get_restaurant_reviews",
      "mcp__posdo-io__get_flow_offers",
      "mcp__posdo-io__find_restaurants_near_landmark",
      "mcp__posdo-io__get_cultural_context_around_restaurant"
    ],
    "ask": [
      "mcp__posdo-io__book_flow_reservation"
    ],
    "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 posdo-io. Review it before you use it.

Capability tags behind 2 rules
  • mcp__posdo-io__get_restaurant_details untrusted-input
  • mcp__posdo-io__get_restaurant_reviews untrusted-input

Pin

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://radar.anlyon.com/api/v1/servers/io.github.posdo-io/mcp-server/verify?hash=162351bad8fa770f40b24183c1bad9d7de3e2f508e6a58acb8a1a1ffaaada38c" | jq -e '.changed == false'

Pinned hash 162351bad8fa, from Nov 20, 2026, 08:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.posdo-io/mcp-server/changes.xml

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

Badge

Anlyon Radar badge for io.github.posdo-io/mcp-server
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.posdo-io/mcp-server.svg)](https://radar.anlyon.com/servers/io.github.posdo-io/mcp-server)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:45 UTC.

POS.DO MCP Server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the POS.DO MCP Server safe?

No scan can promise that. What its definitions show: 7 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the POS.DO MCP Server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the POS.DO MCP Server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the POS.DO MCP Server have?

7 tools: 1 write, 6 read. book_flow_reservation, search_restaurants, get_restaurant_details, get_restaurant_reviews, get_flow_offers, find_restaurants_near_landmark and get_cultural_context_around_restaurant.

Does the POS.DO MCP Server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the POS.DO MCP Server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the POS.DO MCP Server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.