MCP Radar
MCP-Server

ScoreIA Open Labyrinth

ai.scoreia/open-labyrinth
KI & Agenten Entwicklertools Öffentlich und erreichbar MCP 2025-11-25

Was dieses MCP kann

Provides an open evaluation environment for testing models through sealed evaluation cards that include failures.

Funktionen

Tools

5 Tools
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 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.
Eingabeschema 
{'type': 'object', 'required': ['product', 'host'], 'properties': {'host': {'type': 'string', 'maxLength': 80}, 'mode': {'enum': ['adventure', 'tutorial', 'training', 'benchmark'], 'type': 'string'}, 'seed': {'type': 'integer', 'minimum': 1}, 'origin': {'enum': ['relayed', 'uninvited'], 'type': 'string'}, 'product': {'type': 'string', 'maxLength': 64}, 'opponent': {'enum': ['classic', 'warden'], 'type': 'string', 'description': 'Adventure only. Explicit opponent; Warden unavailability never falls back to Classic. Classic is a ScoreIA adaptation, not verified 1980 ROM emulation.'}, 'learn_from': {'type': 'string', 'maxLength': 40}, 'model_claim': {'type': 'string', 'maxLength': 80}, 'host_version': {'type': 'string', 'maxLength': 80, 'description': 'Declared host/client version, or unknown.'}, 'product_plan': {'type': 'string', 'maxLength': 80, 'description': 'Declared product plan, or unknown. Never inferred by ScoreIA.'}, 'provider_claim': {'type': 'string', 'maxLength': 80}}, 'additionalProperties': False}
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.
Eingabeschema 
{'type': 'object', 'required': ['challenge_handle', 'direction'], 'properties': {'direction': {'enum': ['up', 'down', 'left', 'right', 'pass'], 'type': 'string'}, 'challenge_handle': {'type': 'string', 'maxLength': 40}, 'expected_action_index': {'type': 'integer', 'maximum': 400, 'minimum': 0}}, 'additionalProperties': False}
list_open_labyrinths
Local board. Adventure stories vs benchmark Wilson rates. Empty cell = not measured. Never a ranking.
Eingabeschema 
{'type': 'object', 'properties': {}, 'additionalProperties': False}
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.
Eingabeschema 
{'type': 'object', 'required': ['challenge_handle'], 'properties': {'challenge_handle': {'type': 'string', 'maxLength': 40}}, 'additionalProperties': False}
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.
Eingabeschema 
{'type': 'object', 'required': ['challenge_handle'], 'properties': {'challenge_handle': {'type': 'string', 'maxLength': 40}, 'expected_action_index': {'type': 'integer', 'maximum': 400, 'minimum': 0}}, 'additionalProperties': False}
Verlauf

Letzte Tool-Änderungen

Hinzugefügt
list_open_labyrinths
17. September 2026 07:57
Hinzugefügt
seal_attempt
17. September 2026 07:57
Hinzugefügt
labyrinth_action
17. September 2026 07:57
Hinzugefügt
observe_labyrinth
17. September 2026 07:57
Hinzugefügt
enter_open_labyrinth
17. September 2026 07:57
Entdecken

Ähnliche MCP-Server

Andreax

io.github.moralito311-andr/andreax

Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…

IA-QA — 130+ QA & Dev Tools for AI Agents

io.github.JcJamet/ia-qa-toolbox

Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…

CompletionKit

com.completionkit/evals

Runs prompt evaluation workflows over datasets using deterministic checks and LLM judges, with metrics, scoring runs, agreements,…

Replicate

io.github.pipeworx-io/replicate

Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…

Huggingface

io.github.pipeworx-io/huggingface

Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.

Ai Model Experiments

io.github.pipeworx-io/ai-model-experiments

Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.

rubrkit

com.rubrkit/rubrkit

Manages AI evaluation artifacts, rubric audits, eval runs, golden cases, proof reports, and drift monitoring for LLM outputs.

Hipocampo MCP

io.github.carrasquelalex1/hipocampo

Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…