About POS.DO MCP Server
POS.DO MCP Server gives AI agents access to restaurant discovery data across 20 countries, including reviews, cultural context and time-based offers. Its tools also support finding nearby restaurants and booking eligible offers.
Key features
- 01Search restaurants with filters
- 02Read restaurant profiles and reviews
- 03Find restaurants near landmarks
- 04Explore nearby cultural sites
- 05View offers and book reservations
Use cases
- 01Find restaurants by city, cuisine or price
- 02Check reviews and opening details
- 03Locate dining near a landmark
- 04Book a seat for an off-peak offer
MCP support
Exposes restaurant search, details, reviews, cultural context, offers and reservation tools to MCP clients through a hosted HTTP endpoint.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://pos.do/mcpclaude mcp add --transport http posdo-io https://pos.do/mcp{"mcpServers":{"posdo-io":{"type":"http","url":"https://pos.do/mcp"}}}Open in Cursor{"servers":{"posdo-io":{"type":"http","url":"https://pos.do/mcp"}}}Open in VS Code{"mcpServers":{"posdo-io":{"type":"http","url":"https://pos.do/mcp"}}}{"mcpServers":{"posdo-io":{"serverUrl":"https://pos.do/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
7| Parameter | Type | Required | Description |
|---|---|---|---|
| city | string | Yes | City name. Examples: 'Madrid', 'New York', 'Milano', 'Barcelona'. |
| limit | integer | No | |
| query | string | No | Free-text search: cuisine, occasion, features (e.g. 'romantic italian terrace'). |
| cuisine | string | No | Cuisine filter. Examples: 'italian', 'mexican', 'sushi', 'spanish', 'indian'. |
| features | string | No | Comma-separated feature filters: terrace, wifi, parking, delivery, accessible. |
| price_max | integer | No | Max price level 1=budget, 4=fine dining. |
Details
From the project READMEPOS.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-Keyheader)
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:
{
"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:
{
"mcp.servers": {
"pos-do": {
"url": "https://pos.do/mcp",
"transport": "http"
}
}
}
Generic MCP client (raw JSON-RPC over HTTP)
curl -sS -X POST https://pos.do/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Tools
| Tool | Purpose | Docs |
|---|---|---|
search_restaurants | Search restaurants in a city, with cuisine/price/feature filters | docs |
get_restaurant_details | Full profile for a restaurant by slug | docs |
get_restaurant_reviews | Paginated reviews with star and date filters | docs |
get_flow_offers | Today's time-based discount slots for a restaurant | docs |
book_flow_reservation | Reserve a seat at a Flow-discounted slot | docs |
find_restaurants_near_landmark | Restaurants within walking distance of a famous landmark | docs |
get_cultural_context_around_restaurant | Monuments, 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 (fulltools[]withinputSchema)https://pos.do/.well-known/webmcp.json— webmcp.link manifesthttps://pos.do/.well-known/mcp/server-card.json— Smithery-style server cardhttps://pos.do/mcp/manifest.json— alias
Authentication and rate limits
The server runs in anonymous tier by default. No API key required.
| Tier | Per minute | Per day |
|---|---|---|
| Anonymous (default) | 60 req/min per IP | 10,000 req/day per IP |
| Reservation attempts | 10/min per IP | 5/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
- Issues / feature requests: github.com/posdo-io/mcp-server/issues
- Operator: EZZYPUSH SL (Spain)
- Website: pos.do
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.