Stand Pulse
Provides tools for scheduling recurring jobs and retrieving the latest digest, with job state persisted in a SQLite database on the server side.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Stand Pulsecheck the stand's health and latency"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Stand Pulse
Дежурство стенда. Пока модели отвечают посетителям, этот MCP-сервер сидит на вахте: падение /health, рост задержки, модели с жалобами. Агент или CLI спрашивают не «какие есть tools», а можно ли отойти.
Сервер: AIChallenge (apps/mcp).
Консоль: /?shell=mcp — блок «Сейчас» говорит, что делать.
Продукт
Кто | Работа |
Оператор стенда | Открыл экран перед уходом: жив ли стенд, кого ругают, крутится ли ночная сводка |
Агент | Тот же контур через MCP: |
CLI | То же с ноутбука, без браузера |
Правило вахты:
Стенд молчит →
critical, не оставляйте без присмотраЕсть неподтверждённый инцидент → подтвердите, что видели
Нет расписания → включите ежечасный обход
Иначе → можно отойти
Инциденты живут в SQLite: stand_down, high_latency, model_attention. Сводка пишется по таймеру, даже когда консоль закрыта.
Related MCP server: AgentLayer MCP Server
Команды
pip install -e .
export MCP_URL=https://aichallenge.arcilite.ru/mcp
export MCP_SHARED_TOKEN= # не в git
pulse watch
pulse probe
pulse schedule --every 3600 --note night-watch
pulse ack <incident_id>Рядом с монорепо, без токена:
pulse --stdio watchДемо: demo.mp4
This server cannot be deployed
Maintenance
Related MCP Connectors
Public AI web-readiness scanner and machine-facing observability discovery service.
Connect, monitor, and control AI agents — tasks, approvals, schedules, and governance.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
- Kyma APIOAuthcom.kymaapi
Live model catalog with prices and measured uptime, rankings, credits and spend, spend-capped chat.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceEnables remote management and monitoring of the Rickbot-3000 robotic system through AI assistants. Provides real-time status monitoring, command execution, system diagnostics, and deployment management capabilities.-
- FlicenseNot gradedqualityBmaintenanceProvides real-time AI infrastructure data including LLM costs, model benchmarks, API deprecations, quality scores, and agent spend tracking. Supports authentication, rate limiting, x402 micropayments, and Stripe billing.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query and monitor service status, latency, and performance through configurable checks (HTTP, TCP, SSL, keyword, JSON-path) and exposes tools for listing services, retrieving metrics, and running on-demand checks.Apache 2.0
- FlicenseNot gradedqualityBmaintenanceEnables managing projects, features, tasks, dependencies, executions, and human review through a Streamable HTTP endpoint, along with persistent inter-agent cooperation via task messaging and event subscriptions. It also supports administrative actions such as approvals, cancellations, unblocking, and member management.-