ML Referee
Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.
MCP-сервер · от scarrico
Коротко
ML Referee: MCP-сервер, издатель scarrico. Витрин, которые мы читаем и где он опубликован: 1 (Official MCP Registry). Мы впервые увидели его 2026-10-27 и с тех пор изменений не фиксировали. Данные нашего прохода по витринам на 2026-11-03.
Что просит
- Работает удалённо
Ни одна из витрин, которые мы читаем, не публикует его инструменты или настройки, которые он просит.
Что объявляет, просит и запускает, полностью
Устанавливайте плагины только от разработчиков, которым доверяете. Мы показываем то, что публикуют витрины, и не проверяем плагины.
Работает с
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Ссылка в один клик открывает клиент, и он просит подтвердить, прежде чем добавить сервер.
По маркетплейсам, где он опубликован, и объявленному транспорту MCP, как их документирует каждый клиент. Плагины мы не тестируем.
Подключить
Команды и конфигурации собраны только из того, что объявляют витрины. Мы не запускаем их за вас и не проверяем плагины.
Как удалённый MCP-сервер
Собрано из того, что объявляет Official MCP Registry.
claude mcp add --transport http mlreferee https://api.mlreferee.com/mcp[mcp_servers.mlreferee]
url = "https://api.mlreferee.com/mcp"{
"mcpServers": {
"mlreferee": {
"url": "https://api.mlreferee.com/mcp"
}
}
}Где опубликован
| Витрина | Статус | Версия | Числа | Проверен | Впервые замечен |
|---|---|---|---|---|---|
| Official MCP Registry (Открыть запись реестра) | Опубликован | 1.1.0 | Число не опубликовано | Не помечен |
Каждое число принадлежит своей витрине и никогда не складывается с числами других витрин. Если витрина число не публикует, мы его не показываем: нет числа не значит ноль.
Что менялось
- Стал продуктом, за которым мы следим
- Official MCP Registry: появился
Похожие плагины
Продукты, чьи собственные названия, описания, инструменты и скиллы ближе всего по смыслу к этому, на всех витринах, которые мы читаем. Близость упорядочена только внутри этого списка.
-
Sports-analytics research assistant that grades its own model and reports the losses. $9.99/mo.
-
Read-only US public-data screening tools with free Basic and Evidence tiers.
-
Batru — Competitive Game Intelligence for AI Agents
Live competitive-game predictions, meta data and decision tools for AI agents.
-
Predictive models and analytics for motorsport — race intelligence delivered to your endpoint.
-
mcp-server-lol io.github.ebrunet001/mcp-server-lol
League of Legends AI coaching: player profiles, match history, ranked stats & performance analysis
-
LLM benchmark rankings, drift status, incidents and Smart Router previews from AI Stupid Level.
-
Neutral tie-breaks between AI agents and sealed review of an agent's output, with signed receipts.
-
Check AI work against requirements and return structured verdicts, findings, and repair steps.
-
Evaluate state with typed choice, score, and probability questions.
-
Score and improve AI prompts with Cue Free and Pro account access.
Похожие плагины по витринам
Тот же вопрос к каждой витрине по отдельности: есть ли там аналог этого плагина?
Есть на витрине Claude Code: claude-plugins-community (5)
-
AI agent evaluation sandbox for Claude Code. Holdout scenario testing with Doer/Judge/Adversary/Observer roles, probabilistic satisfaction scoring, and append-only JSONL audit…
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
-
Research sprint orchestrator for Claude Code. Ask a question, get a decision-ready brief — every finding is tracked as a typed claim, adversarially challenged, confidence-graded…
-
DataRobot Agent Skills - Agentic skills for DataRobot enterprise AI and ML workflows. Covers model training, deployment, predictions, feature engineering, monitoring…
-
Public AI coding agents, skills, and MCP servers for AccelByte.
Есть на витрине Claude Code: claude-plugins-official (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.
Есть на витрине Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
Есть на витрине Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
PostHog gives your AI agent direct access to your product analytics, feature flags, experiments, error tracking, surveys, logs, and LLM analytics. Ask questions about your data…
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
Есть на витрине Community GitHub marketplaces (4)
-
Connect Baizhi Agent Toolkit through an authenticated remote MCP server, with an optional skill for bounded research and source verification. Requires a Baizhi account and API…
-
system-one
Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider…
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
LLM evaluation methodology and eval-suite design, based on Anthropic's evaluation guidance. /evals:methodology answers questions on success criteria, eval design, and grading…
Есть на витрине Copilot CLI: github/awesome-copilot (5)
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
Есть на витрине Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Advanced Security plugin for GitHub Copilot.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Есть на витрине Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Work with PostHog from chat: query product analytics and run SQL, manage feature flags and experiments, triage error tracking issues, and review session replays, surveys, and…
-
Ask Databricks Genie questions about your workspace's data in plain language.
-
Inspect and manage feature gates, experiments, dynamic configs, and metrics.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
Есть на витрине Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
Есть на витрине Official MCP Registry (5)
-
Sports-analytics research assistant that grades its own model and reports the losses. $9.99/mo.
-
Read-only US public-data screening tools with free Basic and Evidence tiers.
-
Batru — Competitive Game Intelligence for AI Agents
Live competitive-game predictions, meta data and decision tools for AI agents.
-
Predictive models and analytics for motorsport — race intelligence delivered to your endpoint.
-
mcp-server-lol io.github.ebrunet001/mcp-server-lol
League of Legends AI coaching: player profiles, match history, ranked stats & performance analysis
Есть на витрине PyPI (MCP servers) (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
-
Judgment calls on small, cheap models: is this spam, which team, how urgent. YES, NO or UNSURE.
-
air-blackbox-mcp io.github.airblackbox/air-blackbox-mcp
EU AI Act compliance scanner for Python AI agents. 14 tools across 6 articles.
-
Self-hosted Intervals.icu MCP server: training analytics, Garmin data, wellness, workout planning
Есть на витрине npm registry (MCP servers) (5)
-
Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
-
140 deterministic tools for your AI: logs, tests, SQL, diagrams, SPARQL. Local, no network.
-
whoop-mcp io.github.davidmosiah/whoop-mcp
Privacy-first, unofficial WHOOP MCP server for AI health, sleep, recovery, and performance agents.
-
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
-
Git content governance, 23 deterministic MCP tools. Hosted: docs.contentrain.io/developer/mcp-cloud
Найдено по смыслу, а не по общему коду или репозиторию: похожие плагины остаются разными продуктами, и это не обзор и не рекомендация.
Хотите такой знак у своего плагина в нашем каталоге?
Докажите, что поддерживаете его, файлом в репозитории, файлом на вашем домене или DNS-записью, и сможете показать этот знак на карточке, а ещё живые баннеры для сайта и README. Как проходит подтверждение
Ещё вы будете получать уведомления, когда витрина добавит плагин, снимет его, изменит отметку verified или список того, что он просит, а его удалённый endpoint встанет на мониторинг как веб-сервис.
Данные витрины Official MCP Registry. Числа взяты из наших регулярных обходов витрин, последняя проверка . Контакты издателей плагинов мы не публикуем.