Frequently Asked Questions (FAQ) - TV Recommender MCP Server

Q: What is the TV Recommender MCP Server? A: It’s an MCP (Model Context Protocol) server that enhances LLMs with the ability to provide personalized American TV show recommendations by accessing the TMDb API.

Q: What is MCP (Model Context Protocol)? A: MCP is an open protocol standardizing how applications provide context to LLMs, enabling AI models to interact with external data sources and tools.

Q: How does the TV Recommender MCP Server work? A: It connects to the TMDb API via stdio (standard input/output), retrieves TV show information, and uses it to provide recommendations through an LLM client.

Q: What are the key features of this server? A: Key features include genre-based recommendations, similar show suggestions, detailed show information, actor-based recommendations, trending show discovery, and watch provider lookups.

Q: What is TMDb? A: TMDb (The Movie Database) is a community-built movie and TV database. The API provides access to a wealth of information about various TV shows.

Q: How do I install the TV Recommender MCP Server? A: You can install it globally using npm (npm install -g tv-recommender-mcp-server) or by cloning the repository and installing the dependencies.

Q: What is a TMDb API key, and how do I get one? A: A TMDb API key is a unique identifier that allows you to access the TMDb API. You can obtain one for free by creating an account on the TMDb website (https://www.themoviedb.org/).

Q: How do I configure the TMDb API key? A: Set the TMDB_API_KEY environment variable with your API key.

Q: What are the system requirements for running this server? A: You need Node.js installed on your system.

Q: How do I run the server? A: After installing, run the tv-recommender-mcp-server command in your terminal, ensuring the TMDB_API_KEY environment variable is set.

Q: How do I use this server with an LLM client? A: Configure your MCP-compatible LLM client (e.g., Claude Desktop, Cursor) to communicate with the server via stdio.

Q: How do I use this with Cursor? A: Configure the mcp.json file in the .cursor folder of your project.

Q: Can I use this server with Smithery? A: Yes, you can install the service from the Smithery platform (https://smithery.ai).

Q: What tools does the server provide? A: The server offers tools for getting recommendations by genre (get_recommendations_by_genre), finding similar shows (get_similar_shows), getting show details (get_show_details), finding available watch providers (get_watch_providers), advanced show discovery (discover_shows), and more.

Q: What is the discover_shows tool? A: The discover_shows tool allows for more specified show searches using parameters like keywords, genre, year of release, or trending status.

Q: How can I find shows starring a specific actor? A: Use the find_shows_by_actor tool, providing the actor’s name.

Q: Can I get recommendations based on a specific actor’s work? A: Yes, use the get_recommendations_by_actor tool.

Q: How can I find popular or trending shows? A: Use the get_popular_shows and get_trending_shows tools.

Q: How do I find trailers for a show? A: Use the get_show_videos tool with the show’s title.

Q: How do I get the reviews of a show? A: Use the get_show_reviews tool and provide the show’s title.

Q: Is there any rate limiting? A: Yes, be aware of the TMDb API’s rate limits. Implement retry logic or caching if needed.

Q: Is the API key secure? A: The API key is loaded from environment variables and is not hardcoded in the source code. Ensure that the .env file is excluded from version control.

Q: Is this project open source? A: Yes, it is licensed under the MIT license.

Q: Where can I report issues or contribute to the project? A: You can submit issues and pull requests on the GitHub repository.

Q: How do I contribute to the project? A: Fork the repository, make your changes, and submit a pull request.

Q: What is the recommended workflow for contributing? A: Create a new branch for your feature or bug fix, and submit a pull request against the main branch.

Q: Where can I find more detailed documentation? A: Visit the DeepWiki documentation for detailed information about tool usage, architecture, deployment, and more.