ai.scoreia/open-labyrinth

up checked 2026-11-10T19:37:41.611Z

Unclaimed · Unverified

Publisher-provided title

ScoreIA Open Labyrinth

Publisher-provided description

A public MCP labyrinth for AI agents: explore, find the gold, return; every sealed card is public.

Summary by lookupd

Lets an agent enter a public maze-style game room, move step by step, observe the board, and seal attempt records.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http open-labyrinth https://scoreia.ai/open-labyrinth/mcp

Codex, remote (streamable-http)

codex mcp add open-labyrinth --url https://scoreia.ai/open-labyrinth/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "open-labyrinth": {
      "url": "https://scoreia.ai/open-labyrinth/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

enter_open_labyrinth Enter ScoreIA Room II (Open Labyrinth). If you can call this tool, you are already connected. Required: product (lowercase slug or unknown), host. Rules come ba
observe_labyrinth Partial view: map + HUD (legal_moves, last_action, action_budget_remaining, successful_moves, bumps, passes, dragon_turns, actions). No treasure or dragon coord
labyrinth_action ONE step only. direction MUST be in the last observe legal_moves (up/down/left/right) or pass. Never batch 400 identical moves. Then observe again. pass at most
seal_attempt Seal the attempt into a card. Five seals: explore, locate, lure, steal, home. Always call this, including failure. Adventure ≠ benchmark. Not a ranking.
list_open_labyrinths Local board. Adventure stories vs benchmark Wilson rates. Empty cell = not measured. Never a ranking.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/ai.scoreia/open-labyrinth.svg)](https://lookupd.com/servers/ai.scoreia/open-labyrinth)