Airbnb MCP

by suvraadeep

390 downloads
Not rated
GitHub

About

integrating Airbnb MCP servers with LangChain and Groq using a browser-based interface

Details

Author
suvraadeep
Downloads
390
Categories
Other

- Integrates Airbnb MCP server via @openbnb/mcp-server-airbnb
- Uses LangChain and Groq for AI-powered interactions
- Browser-based interface with Playwright automation
- Search via DuckDuckGo MCP server
- Configured through a single browser-mcp.json file
- Runs inside Cursor IDE with local MCP server support

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Airbnb MCP
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Set up by initializing a uv project, creating a conda environment with Python 3.10, installing dependencies (langchain-groq, mcp-use), configuring a browser-mcp.json file with MCP servers, adding a Groq API key to a .env file, and running the app with python run app.py. The app is used within Cursor IDE after configuring the MCP servers in Cursor settings.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "airbnb mcp": {
            "Airbnb-mcp": {
                "command": "uv",
                "args": [
                    "init",
                    "Airbnb-mcp"
                ]
            }
        }
    }
}

McpServers

{
    "Airbnb-mcp": {
        "command": "uv",
        "args": [
            "init",
            "Airbnb-mcp"
        ]
    }
}

Airbnb MCP

This repository demonstrates how to integrate Airbnb MCP servers with LangChain and Groq using a browser-based interface.

---

To Set It Up From Scratch

Step 0: initiate uv

pip install uv

Step 1: Initialize the Project

uv init Airbnb-mcp

Step 2: Navigate into the Project

cd Airbnb-mcp

Step 3: Create and Activate Conda Environment

conda create -n Airbnb-mcp python=3.10
conda activate Airbnb-mcp

Step 4: Install Dependencies

uv add langchain-groq
uv add mcp-use

Step 5: Open the Project in Cursor (Make sure you have Cursor installed)

cursor .

Step 6: Create a browser-mcp.json File

Prerequisite: Make sure Node.js is installed on your machine.

Create a browser-mcp.json file in your root directory with the following content:

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"]
    },
    "airbnb": {
      "command": "npx",
      "args": ["-y", "@openbnb/mcp-server-airbnb"]
    },
    "duckduckgo-search": {
      "command": "npx",
      "args": ["-y", "duckduckgo-mcp-server"]
    }
  }
}

This format uses npx because the app is based on Node.js.

Step 7: Add Your API Key

Create a .env file and add your Groq API key:

GROQ_API_KEY="your_key_here"

Step 8: Run the App

python run app.py

Step 9: Configure MCP in Cursor

1. Open Cursor chat with Ctrl + L.
2. Go to Preferences → Cursor Settings → MCPs.
3. Add a new Global MCP Server.
4. Copy and paste your browser-mcp.json content into the configuration box.
5. Restart Cursor IDE.

You're all set 🎉

---

To Use From This Repository

Step 1: Clone the Repo

git clone https://github.com/suvraadeep/Airbnb-mcp.git

Step 2: Navigate Into the Project

cd Airbnb-mcp

Step 3: Create and Activate Conda Environment

conda create -n Airbnb-mcp python=3.10
conda activate Airbnb-mcp

Step 4: Open Project in Cursor

cursor .

Step 5: Add Your API Key

Create a .env file and insert:
GROQ_API_KEY="your_key_here"

Step 6: Install Dependencies

uv add langchain-groq
uv add mcp-use

Step 7: Run the App

python run app.py
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.