Connect your coding agent to live cloud status over MCP | OutageDeck<br>Skip to content<br>Search⌘KBrowse providers
MCP server<br>Your agent can check whether the cloud is down before it debugs your code<br>OutageDeck ships a remote MCP server: one URL that gives any MCP client live status for every tracked provider, read from each vendor's own official feed about every 10 minutes. No key needed, nothing to install, nothing stored about your agent.
REST API referenceCheck a stack in the browserHigher limits with an API key
Connect<br>MCP is an open protocol, and this is a plain Streamable HTTP server at https://outagedeck.com/api/mcp. It works the same in every client that speaks it. There is no vendor build, no SDK to install, and no key required, so most setups are one line or one paste.<br>ChatGPT (Plus, Pro, Business, and Enterprise)<br>Settings → Connectors → Add custom connector → paste https://outagedeck.com/api/mcp and choose No authentication. The server also exposes the standard search and fetch tools, so it can be used as a research source and every answer it gives carries a citable link back to the provider page or incident it came from.
Claude, on claude.ai and Claude Desktop<br>Settings → Connectors → Add custom connector → paste https://outagedeck.com/api/mcp. The server needs no authentication, so the connector works immediately.
Claude Code<br>Copy<br>claude mcp add --transport http outagedeck https://outagedeck.com/api/mcp<br>Cursor (.cursor/mcp.json)<br>Copy<br>"mcpServers": {<br>"outagedeck": {<br>"url": "https://outagedeck.com/api/mcp"<br>VS Code, Gemini CLI, Windsurf, Zed, and the OpenAI Agents SDK<br>All of them take a remote Streamable HTTP server by URL. Point them at https://outagedeck.com/api/mcp in whatever the client calls its MCP server list. Clients whose connector layer only speaks Server-Sent Events are handled too: request Accept: text/event-stream and the same JSON-RPC comes back as an event stream.
Any MCP client (raw JSON-RPC)<br>Copy<br>curl -X POST https://outagedeck.com/api/mcp \<br>-H "Content-Type: application/json" \<br>-d '{<br>"jsonrpc": "2.0",<br>"id": 1,<br>"method": "tools/call",<br>"params": {<br>"name": "get_provider_status",<br>"arguments": { "provider": "aws" }<br>}'
The tools<br>10 read-only tools cover the questions agents actually ask. Provider arguments accept slugs, vendor names, or product names: "claude" resolves to Anthropic, "gcp" to Google Cloud.<br>get_provider_statusLive status for one tracked provider: overall state, non-operational services, and open incidents, read from the vendor's official status feed. Accepts a slug, provider name, or product name (e.g., "claude" resolves to Anthropic). Use this first for any "is X down?" question.
check_my_stackOne verdict across up to 12 providers: whether any vendor in the list is reporting a problem right now. Use before debugging an integration failure to answer "is it us or them?" in a single call. Returns a shareable status-board link.
list_active_incidentsEvery incident currently open across all tracked providers, most severe first. Optionally filter by severity (critical, major, minor, maintenance). Use to answer "what is down right now?" across the whole cloud landscape.
get_incident_detailsFull detail for one incident: the provider's own update timeline in chronological order, affected services, severity, and resolution state. Pass the incident slug returned by list_active_incidents or get_provider_status. Use to read what the vendor has actually said about an outage.
get_uptimeIndependent uptime record for one provider over a trailing window (7-90 days, default 30), computed from OutageDeck's own observations of the vendor's official feed: share of time free of major outages, strict uptime with partial outages counted as downtime, and total impaired durations.
get_outage_reportA reliability summary across every tracked provider over a trailing window (7-90 days, default 30): incident totals, severity and category breakdowns, the providers hit hardest by major outages, and the longest-running severe incidents. Use to answer "which vendors had outages recently?" or to compare vendor reliability.
search_providersFind tracked providers by name, product name, or fragment ("postgres", "auth", "claude"). Returns slugs to use with the other tools plus each match's current status. Use when a provider argument did not resolve or to discover what OutageDeck tracks.
watch_providerStarts sending the caller outage alerts for one provider, either from the tracked catalog or from their own custom providers. Requires an API key. Alerts are emailed to the account address; the other channels (Slack, Teams, Discord, webhook) are set up on the account page, so no webhook URL ever has to be shared in a conversation.
searchSearch everything OutageDeck tracks: cloud and SaaS providers, and their incident history. Returns citable results with stable ids for the fetch tool. Use for open questions like "who had outages last week" or "find the GitHub Actions incident"; use get_provider_status...