Tripadvisor MCP Server

1# Tripadvisor MCP Server
2 
3A [Model Context Protocol][mcp] (MCP) server for Tripadvisor Content API.
4 
5This provides access to Tripadvisor location data, reviews, and photos through standardized MCP interfaces, allowing AI assistants to search for travel destinations and experiences.
6 
7[mcp]: https://modelcontextprotocol.io
8 
9## Features
10 
11- [x] Search for locations (hotels, restaurants, attractions) on Tripadvisor
12- [x] Get detailed information about specific locations
13- [x] Retrieve reviews and photos for locations
14- [x] Search for nearby locations based on coordinates
15- [x] API Key authentication
16- [x] Docker containerization support
17 
18- [x] Provide interactive tools for AI assistants
19 
20The list of tools is configurable, so you can choose which tools you want to make available to the MCP client.
21 
22## Usage
23 
241. Get your Tripadvisor Content API key from the [Tripadvisor Developer Portal](https://developer.tripadvisor.com/).
25 
262. Configure the environment variables for your Tripadvisor Content API, either through a `.env` file or system environment variables:
27 
28```env
29# Required: Tripadvisor Content API configuration
30TRIPADVISOR_API_KEY=your_api_key_here
31```
32 
333. Add the server configuration to your client configuration file. For example, for Claude Desktop:
34 
35```json
36{
37  "mcpServers": {
38    "tripadvisor": {
39      "command": "uv",
40      "args": [
41        "--directory",
42        "<full path to tripadvisor-mcp directory>",
43        "run",
44        "src/tripadvisor_mcp/main.py"
45      ],
46      "env": {
47        "TRIPADVISOR_API_KEY": "your_api_key_here"
48      }
49    }
50  }
51}
52```
53 
54> Note: if you see `Error: spawn uv ENOENT` in Claude Desktop, you may need to specify the full path to `uv` or set the environment variable `NO_UV=1` in the configuration.
55 
56## Docker Usage
57 
58This project includes Docker support for easy deployment and isolation.
59 
60### Building the Docker Image
61 
62Build the Docker image using:
63 
64```bash
65docker build -t tripadvisor-mcp-server .
66```
67 
68### Running with Docker
69 
70You can run the server using Docker in several ways:
71 
72#### Using docker run directly:
73 
74```bash
75docker run -it --rm \
76  -e TRIPADVISOR_API_KEY=your_api_key_here \
77  tripadvisor-mcp-server
78```
79 
80#### Using docker-compose:
81 
82Create a `.env` file with your Tripadvisor API key and then run:
83 
84```bash
85docker-compose up
86```
87 
88### Running with Docker in Claude Desktop
89 
90To use the containerized server with Claude Desktop, update the configuration to use Docker with the environment variables:
91 
92```json
93{
94  "mcpServers": {
95    "tripadvisor": {
96      "command": "docker",
97      "args": [
98        "run",
99        "--rm",
100        "-i",
101        "-e", "TRIPADVISOR_API_KEY",
102        "tripadvisor-mcp-server"
103      ],
104      "env": {
105        "TRIPADVISOR_API_KEY": "your_api_key_here"
106      }
107    }
108  }
109}
110```
111 
112This configuration passes the environment variables from Claude Desktop to the Docker container by using the `-e` flag with just the variable name, and providing the actual values in the `env` object.
113 
114## Development
115 
116Contributions are welcome! Please open an issue or submit a pull request if you have any suggestions or improvements.
117 
118This project uses [`uv`](https://github.com/astral-sh/uv) to manage dependencies. Install `uv` following the instructions for your platform:
119 
120```bash
121curl -LsSf https://astral.sh/uv/install.sh | sh
122```
123 
124You can then create a virtual environment and install the dependencies with:
125 
126```bash
127uv venv
128source .venv/bin/activate  # On Unix/macOS
129.venv\Scripts\activate     # On Windows
130uv pip install -e .
131```
132 
133## Project Structure
134 
135The project has been organized with a `src` directory structure:
136 
137```
138tripadvisor-mcp/
139├── src/
140│   └── tripadvisor_mcp/
141│       ├── __init__.py      # Package initialization
142│       ├── server.py        # MCP server implementation
143│       ├── main.py          # Main application logic
144├── Dockerfile               # Docker configuration
145├── docker-compose.yml       # Docker Compose configuration
146├── .dockerignore            # Docker ignore file
147├── pyproject.toml           # Project configuration
148└── README.md                # This file
149```
150 
151### Testing
152 
153The project includes a test suite that ensures functionality and helps prevent regressions.
154 
155Run the tests with pytest:
156 
157```bash
158# Install development dependencies
159uv pip install -e ".[dev]"
160 
161# Run the tests
162pytest
163 
164# Run with coverage report
165pytest --cov=src --cov-report=term-missing
166```
167 
168### Tools
169 
170| Tool | Category | Description |
171| --- | --- | --- |
172| `search_locations` | Search | Search for locations by query text, category, and other filters |
173| `search_nearby_locations` | Search | Find locations near specific coordinates |
174| `get_location_details` | Retrieval | Get detailed information about a location |
175| `get_location_reviews` | Retrieval | Retrieve reviews for a location |
176| `get_location_photos` | Retrieval | Get photos for a location |
177 
178## License
179 
180MIT
181 
182---
183 
184[mcp]: https://modelcontextprotocol.io
185