English Français العربية

AIStatusDashboard

Official registry Other

Read-only MCP server for AIStatusDashboard status, incidents, metrics, and fallback recommendations.

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http aistatusdashboard 'https://aistatusdashboard.com/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "aistatusdashboard": {
            "type": "http",
            "url": "https://aistatusdashboard.com/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. AI Status
  2. Stack
  3. Pages
  4. Running locally
  5. Data pipeline
  6. License

AI Status

Is ChatGPT down, or is it just you?

AI Status answers that one question, fast, for the AI apps people actually use: ChatGPT, Claude, Gemini, Grok, Perplexity, DeepSeek, Meta AI, GitHub Copilot, Cursor, Character.AI, and Le Chat.

What makes it different from mirroring an official status page:

  • We test the services ourselves. Cron-driven probes send real requests to each provider every few minutes and record latency and errors (lib/services/provider-probes.ts).
  • We read the official incident feeds for every provider and link to the original source on each incident (lib/services/source-ingestion.ts).
  • Visitors report in. A one-tap "it's broken for me too" button feeds the "is it just you?" verdict, with self-test traffic filtered out.
  • We never fake a green light. If a status can't be verified it renders as "checking", not "operational".

Stack

Next.js (App Router) · Tailwind CSS · Firebase Firestore · Firebase App Hosting.

Pages

  • / — live board for all monitored apps, troubled apps sort first
  • /<app-id> — per-app verdict page (e.g. /chatgpt, /claude)
  • /incidents — outage history with per-incident detail
  • /how-it-works, /about, /privacy, /terms

Running locally

npm install
cp .env.example .env.local   # add Firebase credentials
npm run dev

Tests and checks:

npm run lint
npm run type-check
npm test          # unit tests (jest)
npm run test:e2e  # playwright

Data pipeline

Cron routes under /api/cron/* (protected by CRON_SECRET) poll status pages, run live probes, ingest incident feeds, classify community reports, and send email alerts. Schedules live in Cloud Scheduler; results land in Firestore (incidents, synthetic_probes, casual_reports, provider_status, …).

License

MIT

Frequently asked questions

What is AIStatusDashboard?

Read-only MCP server for AIStatusDashboard status, incidents, metrics, and fallback recommendations.

How do I install AIStatusDashboard?

It runs as a remote server. In Claude Code: claude mcp add --transport http aistatusdashboard 'https://aistatusdashboard.com/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does AIStatusDashboard need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is AIStatusDashboard open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains AIStatusDashboard?

It is published by aistatusdashboard. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.