HasData Airbnb

Airbnb MCP Server

A hosted Airbnb 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.

https://mcp.hasdata.com/mcp?apis=airbnb

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.

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 mcp add --transport http airbnb "https://mcp.hasdata.com/mcp?apis=airbnb" \

--header "x-api-key: HASDATA_API_KEY"

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:

{

"mcpServers": { "airbnb": { "command": "npx", "args": ["-y", "@hasdata/airbnb-mcp"], "env": { "HASDATA_API_KEY": "YOUR_KEY" } } } }

For Python instead of Node, swap the launcher for the PyPI package, which uvx runs without a manual install:

{

"mcpServers": { "airbnb": { "command": "uvx", "args": ["hasdata-airbnb-mcp"], "env": { "HASDATA_API_KEY": "YOUR_KEY" } } } }

Cursor

~/.cursor/mcp.json for every project, or .cursor/mcp.json for one:

{

"mcpServers": { "airbnb": { "url": "https://mcp.hasdata.com/mcp?apis=airbnb", "headers": { "x-api-key": "HASDATA_API_KEY" } } } }

Windsurf

~/.codeium/windsurf/mcp_config.json. Windsurf calls the field serverUrl, not url:

{

"mcpServers": { "airbnb": { "serverUrl": "https://mcp.hasdata.com/mcp?apis=airbnb", "headers": { "x-api-key": "HASDATA_API_KEY" } } } }

VS Code

.vscode/mcp.json in the workspace:

{

"servers": { "airbnb": { "type": "http", "url": "https://mcp.hasdata.com/mcp?apis=airbnb", "headers": { "x-api-key": "HASDATA_API_KEY" } } } }

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

Two tools, read-only. Samples below are trimmed from real calls, and the numbers move as Airbnb updates. Read them as shapes. Each tool name links to its endpoint reference, which carries the full field list.

The samples are the payload, not the whole response. A tools/call result carries one text block, and that text is itself JSON holding url, status, text and json, with the scraped data under json. From a raw JSON-RPC response the path is result.content[0].text, parsed, then .json. A chat client unwraps that for you and code talking to the endpoint directly does not.

Get Airbnb listings

hasdata_airbnb_listing_getAirbnbListings

A page of search results by place name and dates, or by a map area.

checkIn is always required. Beyond it the tool takes either a location or a full map bounding box, and a box counts only when all four corners are present. Three of the four fail with requiredIfExistsAny on the missing one. A box searches an area Airbnb has no name for, which a place name cannot express.

Returns a properties array and pagination, whose nextPageToken and pageTokens walk the result set. Each property carries id, url, title, latitude, longitude, a short description tagline, a photos array, rating, reviews, a badges array such as Guest favorite or Superhost, and a price object. price holds originalPrice, an optional discountedPrice when the stay is discounted, a qualifier like for 3 nights, and a breakdown.

A search result is intentionally light. Beds, baths, amenities, the host and the full description are not here, they come from the property tool below. Do not expect a bedroom count on a search result.

{

"id": "17545365", "url": "https://www.airbnb.com/rooms/17545365", "title": "Home in East Austin", "latitude": 30.25741, "longitude": -97.73366, "description": "Downtown Casa - neighborhood feel, close to it all", "rating": 4.87, "reviews": 601, "badges": ["Guest favorite"], "price": { "originalPrice": "$607", "discountedPrice": "$447", "qualifier": "for 3 nights", "breakdown": [{ "description": "3 nights x $149.00", "price": "$447.00" }] } }

Get Airbnb property details

hasdata_airbnb_property_getAirbnbPropertyDetails

One listing in full, by its URL.

Returns title, an overview array like ["4 guests", "2 bedrooms", "2 beds", "2 baths"], the full description, rating, reviews, address, latitude, longitude, a photos array, guestCapacity, a host object, an amenities array, and safetyAndPropertyInfo. The host object carries name, isSuperhost, isVerified, the host's own reviews, rating and yearsHosting. Each amenity carries a title, a type, an optional description and an available flag, so a filter reads available, it does not assume every listed amenity is present.

{

"id": "17545365", "title": "Downtown Casa - neighborhood feel, close to it all", "overview": ["4 guests", "2 bedrooms", "2 beds", "2 baths"], "rating": 4.87, "reviews": 601, "address": "Austin, Texas, United States", "guestCapacity": 4, "host": { "name": "Deanna", "isSuperhost": true, "isVerified": true, "reviews": 1273, "rating": 4.86, "yearsHosting": 11 }, "amenities": [ { "title": "Wifi", "type": "SYSTEM_WI_FI", "available": true }, { "title": "Free washer – In unit", "type": "SYSTEM_WASHER", "available": true } ] }

Errors and failure paths

Your client almost never sees an HTTP error code from a tool call. The MCP layer answers 200 and puts the failure inside the result, with isError set to true and the reason as text. The agent reads a message where you might expect a status line.

A wrong key surfaces as tool output, not as a failed connection. tools/list accepts any non-empty key and returns both tools, so the client completes its handshake and shows green. The first tool call then comes back with isError: true and the text HasData API error: 401 Unauthorized. Watch for that string, because nothing earlier in the flow reports the problem.

**A missin