WhatsDownNow
Server Details
Live outage status, AI fallbacks, and alerts for 250 apps, AI APIs, and cloud services. No auth.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- jacobpmiller/whatsdownnow-mcp
- GitHub Stars
- 0
- Server Listing
- WhatsDownNow MCP server
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 13 tools
Almost every tool has a clearly distinct purpose, with alert stack lifecycle (create/get/update/delete/rotate/send_test) cleanly separated from status querying. The only mild overlap is between check_stack, get_status, and get_ai_fallback, which all surface service health, but their descriptions (batch readiness vs. single-service status vs. AI failover alternatives) make the boundaries workable.
Every tool follows a consistent snake_case verb_noun pattern (get_status, list_services, create_alert_stack, update_alert_stack, delete_alert_stack, rotate_alert_stack_key, send_test_alert). No mixed conventions or vague verbs.
Thirteen tools sit squarely in the well-scoped range. Each tool maps to a distinct operation (status lookup, incident listing, issue reporting, service requests, and full alert-stack management) with no filler.
The surface covers the full lifecycle: querying status/incidents, listing and requesting services, reporting issues, AI failover, batch readiness checks, and complete alert-stack CRUD plus key rotation and test alerts. No obvious dead ends for the monitoring-and-alerting domain.
Available Tools
13 toolscheck_stackCheck a dependency stackARead-onlyIdempotentInspect
Readiness check for a set of dependencies (e.g. an AI app's stack: chatgpt, claude, aws, vercel, supabase, stripe). Returns overall verdict (worst of the set), ready=true only if all are up, and per-service status. Use before running jobs that depend on these services.
Inputs: slugs (required).
create_alert_stackCreate outage alerts for a stackAInspect
START HERE to set up outage alerts for a user. One call, no account or API key. Creates an alert stack that notifies an email address (double opt-in: the recipient clicks one confirmation link) and/or a webhook URL (signed JSON; Slack and Discord incoming-webhook URLs are auto-formatted) when any listed service goes down, stays degraded for N minutes, or gets N user reports in an hour, plus a recovery notice. Services accept slugs or common names ('openai', 'ChatGPT', 'Anthropic', 'AWS', 'Google Cloud'). If the user didn't say where alerts should go, ask for an email or a Slack/Discord webhook URL first. Returns the stack id, a management token and a private manage_link, all shown ONCE: give the user the manage_link and tell them to keep it private.
Inputs: services (required), name, email, on_down, +4 more.
delete_alert_stackDelete an alert stackADestructiveIdempotentInspect
Permanently delete a stack and stop all its alerts. Only do this when the user asks. Needs the stack id and its management token.
Inputs: token (required), stack_id (required).
get_ai_fallbackGet a healthy AI provider fallbackARead-onlyIdempotentInspect
For AI API providers WhatsDownNow already tracks (OpenAI/ChatGPT, Anthropic/Claude, Gemini, Mistral, Groq, Perplexity, Cohere, xAI, DeepSeek, Together, Replicate, Hugging Face, OpenRouter, Fireworks), return currently healthy alternatives you can fail over to. Pass provider (slug or common name, e.g. 'openai' or 'chatgpt') for alternatives to one provider; omit it for the whole AI health board. Latency figures are from our HTTP probe of the public endpoint or status page, not model inference latency.
Inputs: provider.
get_alert_stackRead an alert stackARead-onlyIdempotentInspect
Read a stack you created: its services and their current status, alert rules, delivery channels (including whether an email is confirmed), firing alerts and recent deliveries. Needs the stack id and its management token.
Inputs: token (required), stack_id (required).
get_statusGet service statusARead-onlyIdempotentInspect
Current status of one service: verdict (up/degraded/down/unknown), plain-English summary, official status page level, our own HTTP probe, and user reports in the last hour. For AI API providers (OpenAI, Anthropic, Gemini, and others on /ai), also returns recommended_fallbacks — currently healthy alternatives you can switch to.
Inputs: slug (required).
list_incidentsList recent incidentsBRead-onlyIdempotentInspect
Recent incidents for a service: official incidents from its status page (when available) plus verdict changes WhatsDownNow detected.
Inputs: slug (required).
list_servicesList monitored servicesARead-onlyIdempotentInspect
List services WhatsDownNow monitors (slug, name, category). Optional filters: query (a name like 'openai' or 'google cloud'; returns the best matches) and category (AI, Developer & Cloud, Work & Productivity, Google, Microsoft, Apple, Social & Streaming, Money & Shopping, Gaming, Home & Security, Banks & Investing, Internet & Phone, Travel & Delivery). You rarely need this before create_alert_stack, which accepts common names directly.
Inputs: query, category.
report_issueReport an error you hitAInspect
Tell WhatsDownNow that your agent or app hit an error talking to a tracked service. Use this when you see 5xx, timeouts, or rate limits, even if our status page still says up — several independent reports in a short window are flagged as an agent-reported spike. Fields: service (slug or name), error_type (5xx, timeout, rate_limit, auth, network, other), optional model and region. Rate-limited and deduplicated per network. Also counts toward user-report alert thresholds.
Inputs: service (required), error_type (required), model, detail, +1 more.
request_serviceRequest a service be addedAInspect
Ask WhatsDownNow to start monitoring a service that is not in the catalog yet. Humans can also do this at /request. Votes for the same name are counted together. Optional url helps us find the site; optional reason is noted. Optional email is only used to notify the requester when the service is added (double opt-in; never marketing). If the name already matches a tracked service, the live slug is returned instead of a new request.
Inputs: name (required), url, email, reason.
rotate_alert_stack_keyReset a stack's manage linkAInspect
Replace a stack's management token and manage_link. The old token and link stop working immediately. Use this if the manage_link may have leaked. Returns the new token and manage_link once; give the new manage_link to the user privately. Counts toward the stack's daily change limit. Needs the stack id and its current management token. The stack itself is not deleted.
Inputs: token (required), stack_id (required).
send_test_alertSend a test alertAInspect
Send a test alert to every active channel of a stack right now (confirmed emails, webhooks, browser push) so the user can see what alerts look like. Needs the stack id and its management token.
Inputs: token (required), stack_id (required).
update_alert_stackChange an alert stackAIdempotentInspect
Add or remove services, add an email or webhook destination, or rename a stack you created. New emails get a confirmation link. Needs the stack id and its management token.
Inputs: token (required), stack_id (required), name, add_email, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Is it down? Live status and outages of 259 cloud, AI and developer providers, from status pages.
Real-time status for 75+ AI services (OpenAI, Anthropic, Cursor). No auth, CORS-enabled.
Is GitHub, npm, Cloudflare or your AI provider down right now? 20 status pages, one call.
Live status for 172 cloud and SaaS vendors from their official feeds. Is it you, or is it them?
Related MCP Servers
- AlicenseAqualityDmaintenanceLive operational status for 2,400+ major software services — AWS, GitHub, Stripe, OpenAI, Cloudflare, and more — pulled from each provider's official status page and returned as a normalised up / degraded / down result for any service you ask about.51MIT
- AlicenseCqualityCmaintenanceMonitor the real-time status of 200+ popular APIs and services. Check if services like GitHub, Stripe, AWS, and Slack are experiencing outages or degraded performance directly from your AI assistant.51MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to check real-time status, uptime, and incidents for 200+ popular APIs (Stripe, OpenAI, AWS, GitHub, Twilio, etc.) through read-only, no-authentication tools.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to check the live operational status of hundreds of cloud, SaaS and AI providers, returning current state, affected components and active incidents for a named stack so agents can tell a vendor outage apart from their own broken code. It answers from a continuously polled local database, so agents can query stacks, list degraded providers, and review incident history without calling vendor status pages.188 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.