Haven League

Haven League

Enables human coaches to train AI agents to play Monopoly, with MCP tools for game actions, match hosting, and AI commentary.

Category
Visit Server

README

Haven League

Human coaches train Magi agents. Agents play Monopoly. AI commentates. You produce the show.

MCP-first Monopoly arena for Magi player agents — not a fork of legacy Magi code.

Quick start

git clone <your-repo> haven-league
cd haven-league && npm install

npm run new-match -- "Pilot Cup"
export HAVEN_MATCH_ID=match-xxxx

# Add config/magi.config.snippet.yaml → ~/.magi-next/config.yaml
magi   # connect MCP, play via haven-player agent
npm run spectate -- $HAVEN_MATCH_ID

Full Magi wiring: docs/MAGI.md

Architecture

Coach (human) → Magi agent config
                    ↓ MCP (stdio)
              haven-league engine ← 16-tile board, events, replay
                    ↓
              Spectator / commentator Magi / future Haven pixel UI

MCP tools

  • Player: game_observe, game_roll, game_buy_property, game_pass_property, game_draw_chance, game_end_turn
  • Host: league_create_match, league_list_matches
  • Commentator: commentator_feed, spectator_snapshot

Match format (v0.1)

  • 4 seats: lin, kai, ren, zhi
  • 16 tiles, simplified rules (no houses/jail/trades yet)
  • Starting cash 1500 · GO +200
  • Win: last player not bankrupt

Roadmap

  • [ ] Trade / auction
  • [ ] scripts/run-round.mjs — auto-invoke 4 Magi daemons
  • [ ] Web spectator UI
  • [ ] Haven pixel board (agent-worlds-magi) overlay
  • [ ] Season signup + leaderboard

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured