HasData/airbnb-mcp

A hosted Model Context Protocol (MCP) server that gives Claude, Cursor, Windsurf and any other MCP client two read-only Airbnb tools. Search stays by place name or map area, and read a single listing in full, all as structured JSON, with no Airbnb developer account and no partner approval.
It reads public listing pages that a signed-out visitor can see.
**1,000 free credits every month, no card required**, which is 100 Airbnb calls.
Contents
- What you need
- Quick start
- Example prompts
- Tools
- Errors and failure paths
- Pricing, free tier and limits
- Tool selection
- How it compares
- FAQ
- HasData links
- Development
- Contributing
- License
What you need
An MCP client and a HasData API key from the dashboard, free to create with no card, and the free tier covers about 100 calls a month at the 10-credit rate. This is a remote server, so the simplest path is a URL and an x-api-key header, with no container to run and no Airbnb developer account anywhere in the flow. A client that only speaks stdio reaches it through a thin launcher, published as @hasdata/airbnb-mcp on npm and hasdata-airbnb-mcp on PyPI, shown below.
Quick start
The server URL is the same for every client. We run it hands-on in Claude Code and Claude Desktop. The other blocks follow each client's own documented format for a remote server.
| Field | Value |
| :--- | :--- |
| URL | https://mcp.hasdata.com/mcp?apis=airbnb |
| Transport | HTTP, streamable |
| Auth header | x-api-key: HASDATA_API_KEY |
Clients with OAuth support can add the same URL as a connector and sign in without putting a key in a config file.
Claude Code
Claude Desktop
Settings, then Connectors, then Add custom connector, then paste https://mcp.hasdata.com/mcp?apis=airbnb and sign in.
For the config-file route, Claude Desktop loads only local (stdio) servers, so it reaches a remote server through a stdio launcher. The @hasdata/airbnb-mcp package is that launcher, and it reads the key from the environment. Add this to claude_desktop_config.json:
For Python instead of Node, swap the launcher for the PyPI package, which uvx runs without a manual install:
Cursor
~/.cursor/mcp.json for every project, or .cursor/mcp.json for one:
Windsurf
~/.codeium/windsurf/mcp_config.json. Windsurf calls the field serverUrl, not url:
VS Code
.vscode/mcp.json in the workspace:
Example prompts
Prompts, not code. Paste one in and the agent picks the tool itself. Each is annotated with the calls it takes, because every successful call costs 10 credits.
> Search Austin stays for two adults from September 15 to 18 and give me the ten highest-rated under $200 a night.
*One call, 10 credits. Rating and nightly price come back on the search result.*
> Take the top result and pull its full amenities, the guest and bedroom count, and the host details.
*One call, 10 credits. Those live on the property page, which the details tool reads by URL.*
> Compare the nightly price of a three-night stay for two guests in Austin against Nashville.
*Two calls, 20 credits, one search per city.*
> For this listing URL, tell me how many beds and baths it has and whether the host is a Superhost.
*One call, 10 credits.*
A search result is deliberately light, enough to rank and shortlist. The amenities, beds, host and full description come from the property call, so a prompt that shortlists then inspects three homes is one search plus three property calls.
Tools
| Tool | What it returns |
| --- | --- |
| hasdata_airbnb_listing_getAirbnbListings | Listing id and url, title, description, coordinates, photos, rating and review count, badges, and a price object holding the stay total, the nightly figure as text and a discounted price when Airbnb shows one. 10 credits a call |
| hasdata_airbnb_property_getAirbnbPropertyDetails | Title, an overview carrying the guest, bedroom, bed and bath counts as text, description, address and coordinates, rating and review count, photos, guest capacity, host profile, amenities with an availability flag each, and safety and property notes. No price. 10 credits a call |