POS.DO MCP Server

io.github.posdo-ioPublished by GitHub account posdo-iov0.1.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableLocation & LifestyleBusiness & Commerce

Overview

AI-generated overview

Remote MCP server for POS.DO restaurant discovery: search 356K+ restaurants, read reviews, find nearby landmarks and book discounted time-slot reservations.

What you can do
  • Search restaurants by city with cuisine, price and feature filters, and fetch full profiles by slug
  • Read paginated reviews with star-rating and date filters
  • List Flow time-based discount offers with remaining covers
  • Book a reservation at a Flow-discounted slot, with idempotent retries
  • Find restaurants near a landmark and get cultural context (monuments, museums, parks) from Wikidata
When to use it
Useful when an assistant needs to recommend places to eat, compare restaurants by reviews or price, plan dining around sightseeing, or book a discounted off-peak table in one of the covered countries.
Requirements
No local install: connect to the remote endpoint at pos.do/mcp over Streamable HTTP. No API key is required; the server runs in an anonymous tier limited to 60 requests per minute and 10,000 per day per IP. Reservation attempts are limited to 10 per minute per IP and 5 per day per email.
Before you install
Booking a reservation creates a real reservation at a restaurant and requires a phone number in E.164 format; send the same Idempotency-Key header on retries to avoid duplicates. Requests go to a third-party operator (EZZYPUSH SL) and are rate limited per IP. Higher-rate API keys are available on request.

Installation

In SourceWeft

  1. Open POS.DO MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.posdo-io%2Fmcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "pos-do": {
      "type": "http",
      "url": "https://pos.do/mcp"
    }
  }
}

README

[POS.DO MCP Server]

PosDO MCP Server

Discovery of 356K+ restaurants across 20 countries via the Model Context Protocol.

[License] [MCP] [Endpoint]

POS.DO is a discovery platform with global coverage of restaurants — names, addresses, reviews, photos, opening hours, cuisines, neighbourhoods, cultural context, and real-time availability with time-based offers. This MCP server exposes that catalogue to AI agents over the Model Context Protocol.

What this server provides

  • 356,780 restaurants in 20 countries (US, ES, IT, MX, FR, CO, DE, GB, DO, PR, AU, CA, PT, JP, BE, CH, HK, VE, NZ, PY)
  • 7 languages of content (ES, EN, IT, FR, DE, PT, CA)
  • 14.1M+ user reviews with author, rating, text, language, photos
  • Cultural context — nearby monuments, museums, parks, and heritage sites from Wikidata, per restaurant
  • Flow time-based offers — off-peak discounts at participating restaurants, with real seat availability
  • Reservation booking with idempotent semantics (safe retries via Idempotency-Key header)

This is a proxy repository. The MCP endpoint runs at https://pos.do/mcp and is operated by EZZYPUSH SL. No local installation of the server is required — agents just point at the URL.

Quick start

Claude Desktop

Add to claude_desktop_config.json:

jsonc
{  "mcpServers": {    "pos-do": {      "url": "https://pos.do/mcp"    }  }}

Restart Claude Desktop. The 7 tools below become available.

Cursor / Cline / Continue

Most MCP clients accept a remote HTTP server entry of the same shape. For Cursor:

json
{  "mcp.servers": {    "pos-do": {      "url": "https://pos.do/mcp",      "transport": "http"    }  }}

Generic MCP client (raw JSON-RPC over HTTP)

bash
curl -sS -X POST https://pos.do/mcp \  -H 'Content-Type: application/json' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

ToolPurposeDocs
search_restaurantsSearch restaurants in a city, with cuisine/price/feature filtersdocs
get_restaurant_detailsFull profile for a restaurant by slugdocs
get_restaurant_reviewsPaginated reviews with star and date filtersdocs
get_flow_offersToday's time-based discount slots for a restaurantdocs
book_flow_reservationReserve a seat at a Flow-discounted slotdocs
find_restaurants_near_landmarkRestaurants within walking distance of a famous landmarkdocs
get_cultural_context_around_restaurantMonuments, museums, parks near a restaurant (Wikidata)docs

Full tool inventory with inputSchema is served live at /.well-known/mcp.json.

Endpoint and transport

  • Production URL: https://pos.do/mcp
  • Protocol: MCP 2024-11-05
  • Transport: HTTP POST (JSON-RPC 2.0), Streamable HTTP compatible
  • Discovery manifests:
    • https://pos.do/.well-known/mcp.json — official MCP discovery (full tools[] with inputSchema)
    • https://pos.do/.well-known/webmcp.json — webmcp.link manifest
    • https://pos.do/.well-known/mcp/server-card.json — Smithery-style server card
    • https://pos.do/mcp/manifest.json — alias

Authentication and rate limits

The server runs in anonymous tier by default. No API key required.

TierPer minutePer day
Anonymous (default)60 req/min per IP10,000 req/day per IP
Reservation attempts10/min per IP5/day per email

Higher-rate API keys are available on request — open an issue.

For idempotent reservations, send an Idempotency-Key HTTP header (any UUID or stable client-side key). Replays within 24 h return the original reservation instead of creating a duplicate.

Coverage and data sources

See docs/data-coverage.md for per-country counts and source attributions.

Examples

Status

Stable. Backwards-compatible changes only at this point. Breaking changes will be announced via CHANGELOG.md and bumped to 2.x.

License

Apache License 2.0 — see LICENSE.

Contact

Source: README.md at commit 676972a

Tools

7

search_restaurants

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.

Parameterscityrequiredlimitquerycuisinefeaturesprice_max

get_restaurant_details

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.

Parametersslugrequired

get_restaurant_reviews

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.

Parametersslugrequiredsortlimitoffsetrating

get_flow_offers

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'.

Parametersdateslugrequired

book_flow_reservation

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.

Parametersslugrequirednotesguest_namerequiredparty_sizeguest_emailrequiredguest_phonerequiredyield_offer_idrequired

find_restaurants_near_landmark

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'.

Parameterscitylimitradiuslandmarkrequired

get_cultural_context_around_restaurant

Get cultural context around a restaurant: nearby monuments, museums, parks, historical sites with distance and heritage status. Powered by Wikidata.

Parametersslugrequired

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts