About PlayTonight
PlayTonight is an MCP server that uses an LLM to suggest games from a user's game library based on conversational preferences. It is for people seeking casual recommendations grounded in their stated genre, mood, or setting preferences.
Key features
- 01Query a game library with an LLM
- 02Refine conversational input into keywords
- 03Recommend games using query keywords
- 04Return game names, genres, and tags
Use cases
- 01Find a game matching a stated mood
- 02Narrow recommendations by genre or setting
MCP support
Exposes game recommendation tools through an MCP server. The documented flow refines conversational input into keywords, then passes them to a recommendation tool.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPlayTonight
PlayTonight is an MCP server for enabling querying of your game library with a LLM for casual suggestions calculated in an intelligent way.
Configuring the Tool
In Open-WebUI, you can configure this tool as follows: TODO: Configuration steps
System Prompt
Set this in your system prompt once the tool is configured:
You have access to an external tool server named PlayTonight, which can recommend video games based on conversational input.
When the user expresses interest in playing a game, use /refine to extract relevant keywords from their message, then pass those keywords to /recommend as a query.
Always prioritize the user’s stated preferences — such as genre, mood, or setting — and avoid using random unless no preferences are given.
When suggesting games, provide the name, genres, and tags returned by the tool server. Only suggest games that were returned by the tool — don’t invent responses. Note: Playtime is returned in minutes. You may want to convert this to hours when presenting it.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.