PlayTonight

Created By
timhoseya year ago
PlayTonight is an MCP server for enabling querying of your game library with a LLM for casual suggestions calculated in an intelligent way.
Overview

what is PlayTonight?

PlayTonight is an MCP server designed to enable users to query their game library using a large language model (LLM) for intelligent and casual game suggestions.

how to use PlayTonight?

To use PlayTonight, configure it in Open-WebUI and set the system prompt to access the external tool server. When a user expresses interest in a game, use the /refine command to extract keywords from their message and pass those to the /recommend command for tailored suggestions.

key features of PlayTonight?

  • Intelligent game recommendations based on user preferences
  • Integration with a conversational interface for ease of use
  • Ability to refine queries based on user input

use cases of PlayTonight?

  1. Suggesting games based on mood or genre preferences.
  2. Assisting users in discovering new games from their existing library.
  3. Enhancing user experience by providing personalized game recommendations.

FAQ from PlayTonight?

  • Can PlayTonight recommend games from any library?

Yes! PlayTonight can query any game library configured within the system.

  • Is PlayTonight free to use?

Yes! PlayTonight is available for free to users who configure it.

  • How accurate are the recommendations?

Recommendations are based on user input and the game library, ensuring relevant suggestions.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
timhosey
Star
0
Language
Python
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago