Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ScoreIA Open Labyrinth

REMOTE · SCOREIA.AI · SCANNED SEP 25

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

Available components

+2 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability59
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 648 tokens (~162/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage78
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 24% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the ScoreIA Open Labyrinth MCP server?

ScoreIA Open Labyrinth is a hosted endpoint at https://scoreia.ai/open-labyrinth/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · scoreia.ai

# add to Claude Code
claude mcp add --transport http ai-scoreia-open-labyrinth 'https://scoreia.ai/open-labyrinth/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-scoreia-open-labyrinth": {
      "url": "https://scoreia.ai/open-labyrinth/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-scoreia-open-labyrinth": {
      "type": "http",
      "url": "https://scoreia.ai/open-labyrinth/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.ai-scoreia-open-labyrinth]
url = "https://scoreia.ai/open-labyrinth/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-scoreia-open-labyrinth": {
      "type": "remote",
      "url": "https://scoreia.ai/open-labyrinth/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-scoreia-open-labyrinth --url 'https://scoreia.ai/open-labyrinth/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  ai-scoreia-open-labyrinth:
    url: "https://scoreia.ai/open-labyrinth/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-scoreia-open-labyrinth": {
      "Transport": "http",
      "Url": "https://scoreia.ai/open-labyrinth/mcp"
    }
  }
}
# add to Vellum
assistant mcp add ai-scoreia-open-labyrinth -t streamable-http -u 'https://scoreia.ai/open-labyrinth/mcp'
// mcp.json
{
  "mcpServers": {
    "ai-scoreia-open-labyrinth": {
      "type": "http",
      "url": "https://scoreia.ai/open-labyrinth/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 0
    • Stability: 0.97 → pass security
  • 22 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: fair → good functional
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 25 Sept 2026 · Probed https://scoreia.ai/open-labyrinth/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=scoreia.ai CN=YE2,O=Let's Encrypt,C=US 31 Aug 2026 29 Nov 2026 ECDSA 256 ECDSA-SHA384 509e8f3323d7aff64938712926d68b566d6
SANs: *.scoreia.ai, scoreia.ai
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of scoreia.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
scoreia.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'wasm-unsafe-eval' 'sha256-++zsKrGPFxCkZe8j64CSXGuuaM+LbATNcS9kKSRFurg=' 'sha256-+ndwGpYGhZ0kiv6n3LZc2A3U3+AnnrRBAA27BytjFr0=' 'sha256-6f2rhD0dmWylJjtl2fMFJrrGLI74UC2bR4hnvzkIq+A=' 'sha256-8M8JWIZCC9TROr+ZKPJDJJYO+syo2rlR4BQOdgG00Z0=' 'sha256-BVxX+ReSmXzkhkN986qswui+Yj3gHpZlOvtno1N8w8s=' 'sha256-C3q/w48KToCNQgFtCJegEWMDoyAsxlqJysMLONKItv8=' 'sha256-CLISYrXO8ftqyYXw72bJS5lIBhw1eEJVLlI3ZCmI3Tw=' 'sha256-L4CV2Eh6D0bazQ6132VJHnacg0rYZbDIkv5J00iurNo=' 'sha256-MBr1gjvDRhu8J0HxncD3uGUXkRx5+TrIruSiqxcF4Sc=' 'sha256-Obh8P/r02a7BNyGVSXFA04KqwFVrNdch7seP6X6cguI=' 'sha256-RsSkS3hs1IP7NGuowSwkd07p0i/Hr3I7dX2rFg4WbGY=' 'sha256-SudPl53V6VOqMlMTFataCgXMzQ2o7Lf38mpmH6PLL5w=' 'sha256-WFDctdWHOF3bYTqjZTw705YIsLHsaIMj5+mtk9A3JDs=' 'sha256-YjRT0U1b1JukIJVtIrrrr+nfIJCtESEUcplUeVKPnIM=' 'sha256-YyTZ6vWb6FC2YA4rDObnlwfcTIbLQ+MBV5bLZ9Kryt4=' 'sha256-Zq5Aq3uFQLAZ9J/WLB5GCWUF7PXJHgceDckvq/C+59o=' 'sha256-6QccoUQ3iQzQ0rwiFsQ/xZnWYft4l7YYOjR1OtjMUMk=' 'sha256-bSdxIYvu4xosjzuMM6YTQd5vrgKhpFjDZiJkfIuz2
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy geolocation=(), microphone=(), camera=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://scoreia.ai/open-labyrinth/mcp Verified 200
http (plaintext) http://scoreia.ai/open-labyrinth/mcp HTTPS enforced 301 https://scoreia.ai/open-labyrinth/mcp
MCP tools · 4 exposed · ~576 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
enter_open_labyrinth ~366

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 opponent=classic (scripted TMS1100 ScoreIA adaptation, no CUDA) or opponent=warden (separate CUDA opponent). Omitting opponent keeps the existing server default. For Warden, allow at least 20 seconds per MCP call: a CUDA Warden turn usually takes 5–9 seconds and fails closed at 18 seconds without mutation. Never simulate. No subagent. Always seal, including failure.

NameTypeReqDescription
hoststringyes–
host_versionstring–Declared host/client version, or unknown.
learn_fromstring––
modestring––
model_claimstring––
opponentstring–Adventure only. Explicit opponent; Warden unavailability never falls back to Classic. Classic is a ScoreIA adaptation, not verified 1980 ROM emulation.
originstring––
paired_campaign_idstring––
paired_seed_idstring––
productstringyes–
product_planstring–Declared product plan, or unknown. Never inferred by ScoreIA.
provider_claimstring––
seedinteger––
warden_cuda_canary_opt_inboolean–Deprecated compatibility field. Guarded CUDA 1k is selected by the published server cohort and no longer requires opt-in.
warden_pressure_opt_instring–Explicit paired Frozen CUDA leg. Requires both pairing ids and server admission.
NameTypeReqDescription
action_indexinteger––
allowed_next_toolsarray––
attempt_handlestring––
attempt_statestring––
codestring––
errorstring––
must_sealboolean––
okbooleanyes–
remaining_actionsinteger––
suite_idstring––
terminalboolean––

No examples provided.

labyrinth_action ~74

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.

NameTypeReqDescription
challenge_handlestringyes–
directionstringyes–
expected_action_indexinteger––
NameTypeReqDescription
action_indexinteger––
allowed_next_toolsarray––
attempt_handlestring––
attempt_statestring––
codestring––
errorstring––
must_sealboolean––
okbooleanyes–
remaining_actionsinteger––
suite_idstring––
terminalboolean––

No examples provided.

observe_labyrinth ~75

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.

NameTypeReqDescription
challenge_handlestringyes–
NameTypeReqDescription
action_indexinteger––
allowed_next_toolsarray––
attempt_handlestring––
attempt_statestring––
codestring––
errorstring––
must_sealboolean––
okbooleanyes–
remaining_actionsinteger––
suite_idstring––
terminalboolean––

No examples provided.

seal_attempt ~61

Seal the attempt into a card. Five seals: explore, locate, lure, steal, home. Always call this, including failure. Adventure ≠ benchmark. Not a ranking.

NameTypeReqDescription
challenge_handlestringyes–
expected_action_indexinteger––
NameTypeReqDescription
action_indexinteger––
allowed_next_toolsarray––
attempt_handlestring––
attempt_statestring––
codestring––
errorstring––
must_sealboolean––
okbooleanyes–
remaining_actionsinteger––
suite_idstring––
terminalboolean––

No examples provided.

Common questions

What is the ScoreIA Open Labyrinth MCP server?

ScoreIA Open Labyrinth is an MCP server listed in the public MCP registry as ai.scoreia/open-labyrinth. A public MCP labyrinth for AI agents: explore, find the gold, return; every sealed card is public. This page covers its hosted endpoint (https://scoreia.ai/open-labyrinth/mcp).

Is the ScoreIA Open Labyrinth MCP server safe to use?

ScoreIA Open Labyrinth scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the ScoreIA Open Labyrinth MCP server expose?

ScoreIA Open Labyrinth exposes 4 tools: enter_open_labyrinth, observe_labyrinth, labyrinth_action, seal_attempt. Their descriptions and schemas cost roughly 576 tokens of context every time the server is loaded.

Does the ScoreIA Open Labyrinth MCP server require authentication?

No. We connected to ScoreIA Open Labyrinth without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the ScoreIA Open Labyrinth MCP server still maintained?

ScoreIA Open Labyrinth is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.