WhatsDownNow

● Active

io.github.jacobpmiller/whatsdownnow

Live outage status, AI fallbacks, and alerts for 250 apps, AI APIs, and cloud services. No auth.

Connect this server

One click to install, or copy the config below. Suits: Cursor · HTTP clients.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "whatsdownnow": {
      "url": "https://whatsdownnow.com/mcp"
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --transport http whatsdownnow https://whatsdownnow.com/mcp
VS Code
code --add-mcp '{"name":"whatsdownnow","type":"http","url":"https://whatsdownnow.com/mcp"}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
APIs & Integrations
Version
1.4.0
Registry
active
Published
11/20/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: WhatsDownNow is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 2 days ago (Nov 20, 2026), 0 open issues.
Official registry
Active
Published as io.github.jacobpmiller/whatsdownnow in the official MCP registry, version 1.4.0.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Hosted by the publisher
Your client talks to whatsdownnow.com: prompts and tool arguments leave your machine for that host.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 07:08 UTCStatus history & uptime →
● Working91 msprotocol 2025-06-18v1.6.0tools

The endpoint answered the MCP handshake as "WhatsDownNow outage status" and listed 13 tools. Answering since Nov 21, 2026.

Context cost ≈ 4.3k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 13 tools.

Tools (13)

  • get_status1 param

    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.

    Show parameters
    • slugstringrequiredService slug or common name, e.g. chatgpt (or 'openai'), claude (or 'anthropic'), aws, stripe. Use list_services to discover slugs.
  • list_services2 params

    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.

    Show parameters
    • querystringService name to look up, e.g. 'OpenAI', 'Cloudflare', 'Chase'
    • categorystringOnly list services in this category
  • check_stack1 param

    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.

    Show parameters
    • slugsarrayrequiredServices to check: slugs or common names, e.g. ['openai', 'stripe', 'vercel']
  • create_alert_stack18 params

    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, Microsoft Teams, Google Chat, Discord, Mattermost and Rocket.Chat incoming-webhook URLs are auto-formatted when the host is recognizable) 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, Teams, Google Chat, Discord, Mattermost or Rocket.Chat 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.

    Show parameters
    • namestringLabel, e.g. 'Acme AI production stack'
    • servicesarrayrequiredServices to watch: slugs or common names, e.g. ['openai', 'stripe', 'cloudflare']
    • webhook_urlstringhttps URL to POST alerts to. Slack, Microsoft Teams (webhook.office.com / Power Automate), Google Chat, Discord, Mattermost (*.mattermost.com) and Rocket.Chat (
    • emailstringEmail address for alerts (recipient must click a confirmation link)
    • on_downbooleanAlert as soon as a service is Down (major outage)
    • degraded_minutesAlert when degraded or down for at least this many minutes; null = off
    • reports_per_hourAlert when user reports in the last hour reach this; null = off
    • componentsarrayOptional official component names to filter official/probe alerts (e.g. ['API']). Empty means all components. User-report alerts still fire even when a componen
    • notify_recoverybooleanAlso send a notice when the service recovers
    • share_enabledbooleanIf true, publish a read-only live status page at a public /s/pub_… URL (does not expose the private stack id). Default off.
    • share_indexbooleanIf true, allow search engines to index the public status page. Requires share_enabled. Default off (noindex). Ignored when a share password is set.
    • share_passwordstringOptional password for the public status page. The page stays unlisted. Password-protected pages cannot be embedded.
    • digest_enabledbooleanIf true, send a weekly email digest of the last 7 days of outages to confirmed addresses on this stack.
    • pagerduty_routing_keystringPagerDuty Events API v2 integration/routing key. Stored on the stack and never returned.
    • opsgenie_api_keystringOpsgenie API key. Stored on the stack and never returned.
    • opsgenie_regionstringOpsgenie API region. Default us.
    • monitor_urlstringOptional https URL of a custom website to check on the existing alerts cadence (SSRF-protected, capped at 3 per stack).
    • monitor_namestringOptional label for monitor_url.
  • get_alert_stack2 params

    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.

    Show parameters
    • stack_idstringrequiredStack id (stk_...) returned by create_alert_stack
    • tokenstringrequiredManagement token (wdn_...) returned once by create_alert_stack
  • update_alert_stack19 params

    Add or remove services, add an email or webhook destination, publish or hide a read-only public status page, or rename a stack you created. New emails get a confirmation link. Needs the stack id and its management token.

    Show parameters
    • stack_idstringrequiredStack id (stk_...) returned by create_alert_stack
    • tokenstringrequiredManagement token (wdn_...) returned once by create_alert_stack
    • add_servicesarraySlugs or names to start watching (default rules)
    • remove_servicesarraySlugs or names to stop watching
    • add_webhook_urlstringAnother https webhook (Slack/Teams/Google Chat/Discord/Mattermost/Rocket.Chat/JSON) to notify
    • add_emailstringAnother email address to notify (must confirm)
    • namestringNew label for the stack
    • share_enabledbooleanPublish (true) or unpublish (false) a read-only live status page. The public URL uses a separate pub_ id, not the private stack id.
    • share_indexbooleanAllow search engines to index the public status page. The page stays noindex unless this is true. Ignored when a share password is set.
    • share_passwordSet a password on the public status page, or null to clear it. Password-protected pages stay unlisted and cannot be embedded.
    • digest_enabledbooleanTurn the weekly email digest on or off for this stack.
    • pagerduty_routing_keystringAdd a PagerDuty Events API v2 routing key. The key is never returned.
    • opsgenie_api_keystringAdd an Opsgenie API key. The key is never returned.
    • opsgenie_regionstringOpsgenie API region for opsgenie_api_key. Default us.
    • monitor_urlstringAdd a custom https website monitor (max 3 per stack).
    • monitor_namestringOptional label for monitor_url.
    • remove_monitor_idstringRemove a custom monitor by id (mon_…).
    • mute_slugstringCatalog service to mute (snooze) on this stack so a known incident does not start a new alert.
    • mute_hoursinteger1–168 hours to mute mute_slug, or 0 to clear the mute. Required when mute_slug is set.
  • send_test_alert2 params

    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.

    Show parameters
    • stack_idstringrequiredStack id (stk_...) returned by create_alert_stack
    • tokenstringrequiredManagement token (wdn_...) returned once by create_alert_stack
  • rotate_alert_stack_key2 params

    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.

    Show parameters
    • stack_idstringrequiredStack id (stk_...) returned by create_alert_stack
    • tokenstringrequiredManagement token (wdn_...) returned once by create_alert_stack
  • delete_alert_stack2 params

    Permanently delete a stack and stop all its alerts. Only do this when the user asks. Needs the stack id and its management token.

    Show parameters
    • stack_idstringrequiredStack id (stk_...) returned by create_alert_stack
    • tokenstringrequiredManagement token (wdn_...) returned once by create_alert_stack
  • list_incidents1 param

    Recent incidents for a service: official incidents from its status page (when available) plus verdict changes WhatsDownNow detected.

    Show parameters
    • slugstringrequiredService slug or common name, e.g. chatgpt (or 'openai'), claude (or 'anthropic'), aws, stripe. Use list_services to discover slugs.
  • request_service4 params

    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.

    Show parameters
    • namestringrequiredService name, e.g. 'Linear' or 'mybank.com'
    • urlstringWebsite or official status page (optional)
    • reasonstringWhy this service should be added (optional)
    • emailstringOptional address to notify when it's added (we send a confirmation link; never marketing)
  • get_ai_fallback1 param

    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.

    Show parameters
    • providerstringAI provider slug or name, e.g. chatgpt, openai, claude, anthropic. Omit to list every AI API we track.
  • report_issue5 params

    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 — reports from 6+ independent networks within 30 minutes are flagged as an 'Unverified agent-report spike' (it never changes the official/probe verdict). 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.

    Show parameters
    • servicestringrequiredService slug or common name, e.g. chatgpt, anthropic, aws
    • error_typestringrequiredWhat you observed
    • modelstringModel id if known, e.g. gpt-4.1 or claude-sonnet-4
    • regionstringRegion or endpoint if known, e.g. us-east-1
    • detailstringOptional short note (no secrets or personal data)

Checked by Serverdex with a plain initialize + tools/list call to whatsdownnow.com/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 21, 2026
Stars
0
Forks
0
Last push
Nov 20, 2026
License
MIT

From the README

WhatsDownNow MCP server Is it down, or is it just you? Live outage status for 250 apps, AI APIs and cloud services, over MCP. Includes healthy AI provider fallbacks and a way for agents to report errors they hit. • Endpoint (Streamable HTTP, no auth): https://whatsdownnow.com/mcp • Docs: https://whatsdownnow.com/developers · OpenAPI: https://whatsdownnow.com/openapi.json • Registry name: io.github.jacobpmiller/whatsdownnow Tools AI board: https://whatsdownnow.com/ai · GET https://whatsdownnow.com/api/v1/ai/health Connect Cursor (~/.cursor/mcp.json) and Claude Desktop use the JSON above. VS Code (.vscode/mcp.json): Claude Code: claude mcp add --transport http whatsdownnow https://whatsdownnow.com/mcp Verdicts combine official status pages with our own HTTP checks about every 11 minutes. Service names belong to their owners; WhatsDownNow is not affiliated with them. The server code is closed source; this repo holds the public listing metadata. Status badges Security issues: see SECURITY.md.

Read the full README on GitHub →

Remotes

  • streamable-httphttps://whatsdownnow.com/mcp

The most-starred APIs & Integrations servers in the index, with their live-check result.

ServerStarsLast pushLive check
OpenWork MCP Gateway24,576Nov 2026Needs sign-in
API Anything3,699Nov 2026Local / not checked
GoModel1,322Nov 2026Local / not checked
Scaleway MCP server1,027Nov 2026Local / not checked
AnythingMCP817Nov 2026Needs sign-in

WhatsDownNow: questions people ask

Is WhatsDownNow a remote or a local MCP server?
According to its entry in the official MCP registry, WhatsDownNow ships as a hosted endpoint (streamable-http) that your client connects to by URL.
Does WhatsDownNow need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is WhatsDownNow safe to use?
Looks healthy: WhatsDownNow is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is WhatsDownNow still maintained?
Active: the repository's last commit 2 days ago. Last push Nov 20, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
What tools does WhatsDownNow expose?
13 tools as listed by the server itself during the live check, including get_status, list_services, check_stack, create_alert_stack, get_alert_stack. The full list with parameters is in the Live check section above.
How do I add WhatsDownNow to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all APIs & Integrations →

Add the badge to your site

Show visitors that WhatsDownNow is listed here — it’s also the link we check for a free listing.

WhatsDownNow — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-jacobpmiller-whatsdownnow?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="WhatsDownNow — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![WhatsDownNow — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-jacobpmiller-whatsdownnow?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/io-github-jacobpmiller-whatsdownnow) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/io-github-jacobpmiller-whatsdownnow) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/io-github-jacobpmiller-whatsdownnow)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/io-github-jacobpmiller-whatsdownnow"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-jacobpmiller-whatsdownnow"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-jacobpmiller-whatsdownnow"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).