Skip to main content
Glama
ampcome-mcps

Airbnb Search & Listings

by ampcome-mcps

airbnb_search

Search Airbnb listings by location, dates, and filters like price and guests to find accommodations with direct booking links.

Instructions

Search for Airbnb listings with various filters and pagination. Provide direct links to the user

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
locationYesLocation to search for (city, state, etc.)
placeIdNoGoogle Maps Place ID (overrides the location parameter)
checkinNoCheck-in date (YYYY-MM-DD)
checkoutNoCheck-out date (YYYY-MM-DD)
adultsNoNumber of adults
childrenNoNumber of children
infantsNoNumber of infants
petsNoNumber of pets
minPriceNoMinimum price for the stay
maxPriceNoMaximum price for the stay
cursorNoBase64-encoded string used for Pagination
ignoreRobotsTextNoIgnore robots.txt rules for this request

Implementation Reference

  • Tool schema and definition for 'airbnb_search', specifying input parameters including location, dates, guest counts, price range, pagination cursor, and robots.txt ignore flag.
    const AIRBNB_SEARCH_TOOL: Tool = {
      name: "airbnb_search",
      description: "Search for Airbnb listings with various filters and pagination. Provide direct links to the user",
      inputSchema: {
        type: "object",
        properties: {
          location: {
            type: "string",
            description: "Location to search for (city, state, etc.)"
          },
          placeId: {
            type: "string",
            description: "Google Maps Place ID (overrides the location parameter)"
          },
          checkin: {
            type: "string",
            description: "Check-in date (YYYY-MM-DD)"
          },
          checkout: {
            type: "string",
            description: "Check-out date (YYYY-MM-DD)"
          },
          adults: {
            type: "number",
            description: "Number of adults"
          },
          children: {
            type: "number",
            description: "Number of children"
          },
          infants: {
            type: "number",
            description: "Number of infants"
          },
          pets: {
            type: "number",
            description: "Number of pets"
          },
          minPrice: {
            type: "number",
            description: "Minimum price for the stay"
          },
          maxPrice: {
            type: "number",
            description: "Maximum price for the stay"
          },
          cursor: {
            type: "string",
            description: "Base64-encoded string used for Pagination"
          },
          ignoreRobotsText: {
            type: "boolean",
            description: "Ignore robots.txt rules for this request"
          }
        },
        required: ["location"]
      }
    };
  • Core handler function for executing 'airbnb_search'. Constructs Airbnb search URL with filters, respects robots.txt, fetches HTML, parses embedded client data JSON using Cheerio, extracts listings with details like ID, description, price, ratings, and generates direct room URLs, supports pagination.
    async function handleAirbnbSearch(params: any) {
      const {
        location,
        placeId,
        checkin,
        checkout,
        adults = 1,
        children = 0,
        infants = 0,
        pets = 0,
        minPrice,
        maxPrice,
        cursor,
        ignoreRobotsText = false,
      } = params;
    
      // Build search URL
      const searchUrl = new URL(`${BASE_URL}/s/${encodeURIComponent(location)}/homes`);
      
      // Add placeId
      if (placeId) searchUrl.searchParams.append("place_id", placeId);
      
      // Add query parameters
      if (checkin) searchUrl.searchParams.append("checkin", checkin);
      if (checkout) searchUrl.searchParams.append("checkout", checkout);
      
      // Add guests
      const adults_int = parseInt(adults.toString());
      const children_int = parseInt(children.toString());
      const infants_int = parseInt(infants.toString());
      const pets_int = parseInt(pets.toString());
      
      const totalGuests = adults_int + children_int;
      if (totalGuests > 0) {
        searchUrl.searchParams.append("adults", adults_int.toString());
        searchUrl.searchParams.append("children", children_int.toString());
        searchUrl.searchParams.append("infants", infants_int.toString());
        searchUrl.searchParams.append("pets", pets_int.toString());
      }
      
      // Add price range
      if (minPrice) searchUrl.searchParams.append("price_min", minPrice.toString());
      if (maxPrice) searchUrl.searchParams.append("price_max", maxPrice.toString());
      
      // Add room type
      // if (roomType) {
      //   const roomTypeParam = roomType.toLowerCase().replace(/\s+/g, '_');
      //   searchUrl.searchParams.append("room_types[]", roomTypeParam);
      // }
    
      // Add cursor for pagination
      if (cursor) {
        searchUrl.searchParams.append("cursor", cursor);
      }
    
      // Check if path is allowed by robots.txt
      const path = searchUrl.pathname + searchUrl.search;
      if (!ignoreRobotsText && !isPathAllowed(path)) {
        log('warn', 'Search blocked by robots.txt', { path, url: searchUrl.toString() });
        return {
          content: [{
            type: "text",
            text: JSON.stringify({
              error: robotsErrorMessage,
              url: searchUrl.toString(),
              suggestion: "Consider enabling 'ignore_robots_txt' in extension settings if needed for testing"
            }, null, 2)
          }],
          isError: true
        };
      }
    
      const allowSearchResultSchema: Record<string, any> = {
        demandStayListing : {
          id: true,
          description: true,
          location: true,
        },
        badges: {
          text: true,
        },
        structuredContent: {
          mapCategoryInfo: {
            body: true
          },
          mapSecondaryLine: {
            body: true
          },
          primaryLine: {
            body: true
          },
          secondaryLine: {
            body: true
          },
        },
        avgRatingA11yLabel: true,
        listingParamOverrides: true,
        structuredDisplayPrice: {
          primaryLine: {
            accessibilityLabel: true,
          },
          secondaryLine: {
            accessibilityLabel: true,
          },
          explanationData: {
            title: true,
            priceDetails: {
              items: {
                description: true,
                priceString: true
              }
            }
          }
        },
        // contextualPictures: {
        //   picture: true
        // }
      };
    
      try {
        log('info', 'Performing Airbnb search', { location, checkin, checkout, adults, children });
        
        const response = await fetchWithUserAgent(searchUrl.toString());
        const html = await response.text();
        const $ = cheerio.load(html);
        
        let staysSearchResults: any = {};
        
        try {
          const scriptElement = $("#data-deferred-state-0").first();
          if (scriptElement.length === 0) {
            throw new Error("Could not find data script element - page structure may have changed");
          }
          
          const scriptContent = $(scriptElement).text();
          if (!scriptContent) {
            throw new Error("Data script element is empty");
          }
          
          const clientData = JSON.parse(scriptContent).niobeClientData[0][1];
          const results = clientData.data.presentation.staysSearch.results;
          cleanObject(results);
          
          staysSearchResults = {
            searchResults: results.searchResults
              .map((result: any) => flattenArraysInObject(pickBySchema(result, allowSearchResultSchema)))
              .map((result: any) => {
                const id = atob(result.demandStayListing.id).split(":")[1];
                return {id, url: `${BASE_URL}/rooms/${id}`, ...result }
              }),
            paginationInfo: results.paginationInfo
          }
          
          log('info', 'Search completed successfully', { 
            resultCount: staysSearchResults.searchResults?.length || 0 
          });
        } catch (parseError) {
          log('error', 'Failed to parse search results', {
            error: parseError instanceof Error ? parseError.message : String(parseError),
            url: searchUrl.toString()
          });
          
          return {
            content: [{
              type: "text",
              text: JSON.stringify({
                error: "Failed to parse search results from Airbnb. The page structure may have changed.",
                details: parseError instanceof Error ? parseError.message : String(parseError),
                searchUrl: searchUrl.toString()
              }, null, 2)
            }],
            isError: true
          };
        }
    
        return {
          content: [{
            type: "text",
            text: JSON.stringify({
              searchUrl: searchUrl.toString(),
              ...staysSearchResults
            }, null, 2)
          }],
          isError: false
        };
      } catch (error) {
        log('error', 'Search request failed', {
          error: error instanceof Error ? error.message : String(error),
          url: searchUrl.toString()
        });
        
        return {
          content: [{
            type: "text",
            text: JSON.stringify({
              error: error instanceof Error ? error.message : String(error),
              searchUrl: searchUrl.toString(),
              timestamp: new Date().toISOString()
            }, null, 2)
          }],
          isError: true
        };
      }
    }
  • index.ts:138-141 (registration)
    Registration of the 'airbnb_search' tool in the AIRBNB_TOOLS array, which is returned by the listTools MCP request handler.
    const AIRBNB_TOOLS = [
      AIRBNB_SEARCH_TOOL,
      AIRBNB_LISTING_DETAILS_TOOL,
    ] as const;
  • index.ts:661-663 (registration)
    MCP listTools request handler that returns the registered tools including 'airbnb_search'.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: AIRBNB_TOOLS,
    }));
  • index.ts:690-692 (registration)
    Dispatch logic in the MCP callTool request handler that routes 'airbnb_search' calls to the handleAirbnbSearch function.
    case "airbnb_search": {
      result = await handleAirbnbSearch(request.params.arguments);
      break;
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions pagination and providing direct links, which adds some context beyond the input schema. However, it lacks critical behavioral details such as rate limits, authentication requirements, error handling, or what the output looks like (beyond 'direct links'). For a search tool with 12 parameters and no annotations, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the core purpose in the first sentence. The second sentence adds useful output context. Both sentences earn their place, though it could be slightly more structured (e.g., explicitly noting key filter types).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (12 parameters, no output schema, no annotations), the description is incomplete. It doesn't explain the return format beyond 'direct links,' lacks error handling or rate limit info, and provides minimal guidance on usage. For a search tool with many filters and pagination, more context is needed to help an agent use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so all parameters are documented in the schema itself. The description adds marginal value by mentioning 'various filters and pagination,' which aligns with parameters like minPrice/maxPrice and cursor, but doesn't provide additional semantic context beyond what's in the schema. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search for Airbnb listings with various filters and pagination.' It specifies the verb ('search') and resource ('Airbnb listings'), and mentions key capabilities (filters, pagination). However, it doesn't explicitly differentiate from its sibling 'airbnb_listing_details' beyond the general search vs. details distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides minimal usage guidance. It mentions 'Provide direct links to the user' which hints at output format, but offers no explicit guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. There's no mention of the sibling tool 'airbnb_listing_details' or when to choose one over the other.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ampcome-mcps/airbnb-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server