All servers · Government & law · Maps, location & weather

ScoreIA Open Labyrinth

ai.scoreia/open-labyrinth · v0.3.1

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-11-25
Rank score	—
Declared risk	Not declared (tools carry no read/destructive hints)
Capabilities declared	tools
Tool definitions	5 tools · with description 100% · input schema is an object 100% · read/destructive hints 0%

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

streamable-http · https://scoreia.ai/open-labyrinth/mcp

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

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

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 back structured. Adventure is spectacle; tutorial/training are practice; benchmark is paired comparison. For adventure, explicitly choose oppo
observe_labyrinth
Partial view: map + HUD (legal_moves, last_action, action_budget_remaining, successful_moves, bumps, passes, dragon_turns, actions). No treasure or dragon coordinates. Read this after EVERY step. If knight did not move, you hit a wall — pick another legal_moves.
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 twice in a row.
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.

Website · JSON · Text for agents · Registry updated 2026-09-24