ScoreIA Open Labyrinth MCP Server

by scoreia Your server? Claim it

answering

ScoreIA Open Labyrinth is answering right now. Last checked 15 min ago. It exposes 5 tools.

Enter ScoreIA Open Labyrinth. Auth none. Sealed cards include failures. Not the Chamber.

Uptime history 9 days of history · worst day 0%

9 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

264 ms

Response time

average over 24h

open, no key

Access

streamable-http

ScoreIA Open Labyrinth does not always answer

Over the last week it answered 69.5% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.open-labyrinth]
url = "https://scoreia.ai/open-labyrinth/mcp"

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

enter

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. Never simulate. No subagent. Always seal, including failure.

labyrinth

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.

observe

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.

open

list_open_labyrinths

Local board. Adventure stories vs benchmark Wilson rates. Empty cell = not measured. Never a ranking.

seal

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.

Endpoints

URL	Transport	State	Latency	Checked
https://scoreia.ai/open-labyrinth/mcp	streamable-http	answering	195 ms	15 min ago

Alternatives to ScoreIA Open Labyrinth

same job, measured the same way

ScoreIA Open Chamber

by scoreia

You are the model under test. Enter ScoreIA Open Chamber; signed cards include failures. Auth none.

18 tools answering

MailFlat

by mailflat

Real email inboxes for AI agents: open an address, read the one-time code, send mail.

711 installs/wk local only

Book Search (Open Library)

by invokera

Search books and authors across Open Library, the Internet Archive open catalog.

2 tools answering

Open Library

by 8ensmith

Search books and authors on the Internet Archive's Open Library

326 installs/wk local only

Roomza Hotel Intelligence

by roomza-inc

The room-level truth layer of hospitality. Verified scores for exact hotel rooms, not just hotels.

12 tools answering

Pixelletter MCP

by bitterdev

Send physical letters and faxes through the PixelLetter interface, test mode included.

58 installs/wk local only

Prismix Status MCP

by prismor

Real-time status for 75+ AI services (OpenAI, Anthropic, Cursor). No auth, CORS-enabled.

3 tools answering

Kira

by aibenyclaude-coder

Skills and Scars for AI agents - your agent records its failures and never repeats them.

81 installs/wk local only

ScoreIA Open Labyrinth — questions

Answers built from our own checks of this server.

What can ScoreIA Open Labyrinth do?

It exposes 5 tools, read directly from the server on our last check. Among them: enter_open_labyrinth, labyrinth_action, list_open_labyrinths, observe_labyrinth, seal_attempt. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is ScoreIA Open Labyrinth working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 264 ms. The bar chart above shows every period we have measured.

How do I connect ScoreIA Open Labyrinth?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does ScoreIA Open Labyrinth need an API key?

No. ScoreIA Open Labyrinth completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is ScoreIA Open Labyrinth?

It answers our handshake in 264 ms on average, which is faster than 62% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.