WhatsDownNow MCP server
io.github.jacobpmiller/whatsdownnowjacobpmillerstreamable-httpv1.4.0Scanned
Live outage status, AI fallbacks, and alerts for 250 apps, AI APIs, and cloud services. No auth.
13 tools: 1 can delete or cancel things, 1 do something that can't be undone, 6 change things and 5 only read.
- Reads private data · 2
- Reads text others write · 11
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the WhatsDownNow MCP server can do
The WhatsDownNow MCP server is published by the GitHub account jacobpmiller. It has 13 tools. It can delete or cancel things (1 tool: delete_alert_stack), do things that cannot be undone, such as sending, paying or publishing (send_test_alert) and create or change data (6 tools: check_stack, create_alert_stack, update_alert_stack, rotate_alert_stack_key and 2 more). 5 tools only read.
2 tools read private data (get_alert_stack and get_ai_fallback); 11 tools bring in text other people can write (get_status, list_services, check_stack and 8 more); 3 tools can send data out of your system (create_alert_stack, send_test_alert and request_service). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.4.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
13 tools
Deletes or cancels 1Claude Code: deny
delete_alert_stackPermanently delete a stack and stop all its alerts.No findings
Why it is in this group
- The name "delete_alert_stack" says "delete": a word for removing or ending something.
- The description says "Permanently delete".
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Permanently delete a stack and stop all its alerts. Only do this when the user asks. Needs the stack id and its management token.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Can't be undone 1Claude Code: ask
send_test_alertSend 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.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "send_test_alert" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "send_test_alert" says "send": it sends or publishes something to other people.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 6Claude Code: ask
check_stackReadiness check for a set of dependencies (e.g.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
create_alert_stackSTART HERE to set up outage alerts for a user.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "create_alert_stack" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
report_issueTell WhatsDownNow that your agent or app hit an error talking to a tracked service.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
request_serviceAsk WhatsDownNow to start monitoring a service that is not in the catalog yet.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "request_service" says "request": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
rotate_alert_stack_keyReplace a stack's management token and manage_link.No findings
Why it is in this group
- The description's first verb is "replace": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
update_alert_stackAdd or remove services, add an email or webhook destination, or rename a stack you created.Reads text others writeNo findings
Why it is in this group
- The name "update_alert_stack" says "update": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 5Show 5 read-only tools
get_ai_fallbackFor AI API providers WhatsDownNow already tracks (OpenAI/ChatGPT, Anthropic/Claude, Gemini, Mistral, Groq, Perplexity, Cohere, xAI, DeepSeek, Together, Replicate, Hugging Face, Ope…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_ai_fallback" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_alert_stackRead 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.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_alert_stack" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "email": it reads mail.
- untrusted-inputThe description's first sentence says "read" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_statusCurrent 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.Reads text others writeNo findings
Why it is in this group
- The name "get_status" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_incidentsRecent incidents for a service: official incidents from its status page (when available) plus verdict changes WhatsDownNow detected.Reads text others writeNo findings
Why it is in this group
- The name "list_incidents" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Recent incidents for a service: official incidents from its status page (when available) plus verdict changes WhatsDownNow detected.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_servicesList services WhatsDownNow monitors (slug, name, category).Reads text others writeNo findings
Why it is in this group
- The name "list_services" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
66 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write11
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__whatsdownnow__get_ai_fallback",
"mcp__whatsdownnow__get_alert_stack"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:20 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 8
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 8 tools that change things (1 destructive, 1 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://whatsdownnow.com/mcp: tools/list returned 13 tools to an anonymous client, including delete_alert_stack (destructive), send_test_alert (irreversible), check_stack (write), create_alert_stack (write), update_alert_stack (write) and 3 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 added, 1 changed.+3 added~1 changedView diff
- Added:get_ai_fallbackOnly reads
- Added:report_issueChanges things
- Added:request_serviceChanges things
- Changed:get_statusOnly readsdescription
Install
Pinned to version 1.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http whatsdownnow https://whatsdownnow.com/mcpclaude mcp add --transport http whatsdownnow https://whatsdownnow.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__whatsdownnow__get_status",
"mcp__whatsdownnow__list_services",
"mcp__whatsdownnow__get_alert_stack",
"mcp__whatsdownnow__list_incidents",
"mcp__whatsdownnow__get_ai_fallback"
],
"ask": [
"mcp__whatsdownnow__check_stack",
"mcp__whatsdownnow__create_alert_stack",
"mcp__whatsdownnow__update_alert_stack",
"mcp__whatsdownnow__send_test_alert",
"mcp__whatsdownnow__rotate_alert_stack_key",
"mcp__whatsdownnow__request_service",
"mcp__whatsdownnow__report_issue"
],
"deny": [
"mcp__whatsdownnow__delete_alert_stack"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as whatsdownnow. Review it before you use it.
Capability tags behind 11 rules
- mcp__whatsdownnow__get_status untrusted-input
- mcp__whatsdownnow__list_services untrusted-input
- mcp__whatsdownnow__check_stack untrusted-input
- mcp__whatsdownnow__create_alert_stack untrusted-input, outbound
- mcp__whatsdownnow__get_alert_stack private-data, untrusted-input
- mcp__whatsdownnow__update_alert_stack untrusted-input
- mcp__whatsdownnow__send_test_alert untrusted-input, outbound
- mcp__whatsdownnow__list_incidents untrusted-input
- mcp__whatsdownnow__request_service untrusted-input, outbound
- mcp__whatsdownnow__get_ai_fallback private-data, untrusted-input
- mcp__whatsdownnow__report_issue untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.jacobpmiller/whatsdownnow/verify?hash=f3c86fe1512919a8ba094c69727bd4771f9a40c50942ea3a994ad3c90a502d4a" | jq -e '.changed == false'Pinned hash f3c86fe15129, from Nov 20, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.jacobpmiller/whatsdownnow/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.jacobpmiller/whatsdownnow)Source: MCP Registry · repository. Synced Nov 20, 2026, 01:17 UTC.
WhatsDownNow MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the WhatsDownNow MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 8 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the WhatsDownNow MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: delete_alert_stack.
Can the WhatsDownNow MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: send_test_alert.
What tools does the WhatsDownNow MCP server have?
- 13 tools: 1 destructive, 1 irreversible, 6 write, 5 read. delete_alert_stack, send_test_alert, check_stack, create_alert_stack, update_alert_stack, rotate_alert_stack_key, request_service, report_issue and 5 more.
Does the WhatsDownNow MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the WhatsDownNow MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_alert_stack, send_test_alert and request_service.
Has the WhatsDownNow MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.