openbnb-org/mcp-server-airbnb

Search Airbnb using your AI Agent

What it solves

This project provides a way for AI assistants (like Claude Desktop or Cursor) to search and retrieve detailed information from Airbnb listings. It bridges the gap between an LLM and Airbnb's public data, allowing the AI to perform location-based searches, filter by price and guest count, and extract specific property details without the user having to manually browse the site.

How it works

It is built as a Model Context Protocol (MCP) server. When an AI client requests a search or listing detail, the server uses Node.js and Cheerio to parse Airbnb's public pages. To ensure accurate results for international locations, it integrates with third-party geocoding services (Photon and Nominatim) to translate location strings into precise map bounding boxes before querying Airbnb.

Who it’s for

Users of MCP-compatible AI applications who want their AI assistants to be able to find and book travel accommodations by interacting with Airbnb data in real-time.

Highlights

  • Advanced Search: Supports filtering by date, guest count (adults, children, infants, pets), price range, and property type.
  • Precise Geocoding: Uses external geocoders to prevent the common issue of non-US searches returning incorrect results.
  • Detailed Extraction: Retrieves comprehensive listing data, including categorized amenities, house rules, and direct booking links.
  • Flexible Installation: Available as an MCP Bundle (.mcpb) for one-click installation in Claude Desktop or via npx for other clients.
  • Compliance: Respects robots.txt by default and includes rate-limiting awareness.

Related

  • Project
    mapbox/mcp-server

    A Model Context Protocol server that gives AI agents access to Mapbox's location intelligence, enabling geospatial reasoning, routing, and interactive map visualization.

  • Project
    anysearch-ai/anysearch-mcp-server

    AnySearch MCP Server is a real‑time, MCP‑compatible backend that provides general web search, vertical‑domain search, parallel batch search, and URL‑content extraction. It works with popular AI‑assistant IDEs (OpenCode, Claude Code, Cursor, VS Code, Windsurf, Cline) via simple JSON configuration, supports optional API‑key authentication for higher rate limits, and even allows anonymous use. The README details registration, key handling, client‑specific config snippets, and the four tool endpoints (`search`, `get_sub_domains`, `batch_search`, `extract`).

  • Project
    AminForou/mcp-gsc

    An MCP server that connects Google Search Console to AI assistants, enabling natural language analysis of SEO data, indexing audits, and sitemap management.

  • Project
    johnhuang316/code-index-mcp

    An MCP server that provides intelligent code indexing and AST-based analysis to help AI assistants navigate and understand complex codebases.

  • Project
    blazickjp/arxiv-mcp-server

    A local MCP server that enables AI agents to perform deep literature research on arXiv, featuring section-level LaTeX reading, citation tracking, and topic monitoring.