{
  "markdown": "# @pipeworx/statuspage\n\nService status / uptime MCP — \"is X down right now?\" answered from vendors' own\nAtlassian Statuspage feeds. Keyless.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\nAtlassian Statuspage is a de-facto standard: hundreds of vendors expose the same\nJSON contract at `https://<status-host>/api/v2/status.json`. This pack reads that\ncontract, so it closes a class of question rather than one vendor.\n\n## Tools\n\n- `statuspage_check(vendor | status_host, include_components?)` — current status for\n  one vendor: overall indicator, the vendor's own status line, every degraded\n  component, open incidents with the latest update text, and upcoming maintenance\n  where published.\n- `statuspage_incidents(vendor | status_host, unresolved_only?, limit?, include_all_updates?)`\n  — incident history: title, lifecycle status, impact, start/resolve times,\n  duration, affected components, latest update.\n- `statuspage_list_vendors(category?, query?, include_elsewhere?)` — the vendors this\n  pack can answer for, with each one's status host, so a name can be confirmed\n  rather than guessed.\n- `statuspage_multi_check(vendors[])` — up to 20 vendors in one call, returned as a\n  compact up/down table plus a roll-up. Hosts are de-duplicated, concurrency capped\n  at 5.\n\n## Coverage\n\nCoverage is **the curated vendor map plus any caller-supplied host.**\n\nThe curated map holds **190 vendors** across AI/model providers, cloud and hosting,\ndatabases and observability, developer tools, payments and fintech, communications,\nand business SaaS.\n\n**Every host in the map was verified, not guessed.** 206 candidate hosts were probed\nlive; each survivor had to return a parseable Statuspage v2 payload on\n`/api/v2/status.json`, `/api/v2/summary.json` *and* `/api/v2/incidents.json`.\nCandidates that failed were dropped rather than shipped on a hunch — status\nhostnames are genuinely unguessable (`status.anthropic.com` redirects to\n`status.claude.com`; `status.cloudflare.com` does not resolve at all, the real host\nis `www.cloudflarestatus.com`).\n\nThe second wave (67 vendors, taking the map from 123 to 190) came from a coverage\naudit against a competing tracker: the bottleneck was never the host pattern, it was\nknowing which vendor NAMES to try. Given the names, 68 of 78 resolved on the first\nor second guess of the ordinary pattern, and 67 survived the three-endpoint check\n(`kong` was dropped — `status.konghq.com` answers 418 to a non-browser client).\n\nFor anything outside the map, pass `status_host: \"status.somevendor.com\"`. Every\nresponse says which of the two it used via the `source` field\n(`curated_map` | `caller_supplied_host`).\n\n### Vendors that publish status elsewhere\n\nRoughly 43 well-known companies were probed and found to publish status in some\nother format — AWS, Google Cloud, Azure, Slack, Stripe, GitLab, Heroku, PagerDuty,\nNotion, Databricks and others. Asking for one of those returns\n`reason: 'vendor_not_statuspage'` together with the URL a human should open, rather\nthan nothing. `statuspage_list_vendors({include_elsewhere: true})` lists them.\n\n### Statuspage \"lite\" hosts\n\n17 hosts in the map serve `status.json` / `summary.json` / `incidents.json` but omit\n`/api/v2/incidents/unresolved.json` (OpenAI is one). The pack falls back to filtering\nthe incident feed for open incidents, and reports which path it used in\n`incidents_source`.\n\n## Result semantics\n\n- **\"All Systems Operational\" is a positive result**, returned as `found: true`\n  with `operational: true` and an empty `open_incidents` array.\n- **A vendor with no incidents and a status page we could not read never look the\n  same.** A fetch failure returns `found: false, reason: 'status_page_unreachable'`.\n- An unrecognised vendor returns `found: false, reason: 'vendor_not_covered'` with\n  near matches and a pointer to `statuspage_list_vendors` — never a guessed host,\n  never a silently substituted vendor.\n\n## Data source\n\nAtlassian Statuspage v2 REST API, served by each vendor on its own status host:\n\n- `/api/v2/status.json` — overall indicator + description\n- `/api/v2/summary.json` — status + components + active incidents + maintenance\n- `/api/v2/incidents.json`, `/api/v2/incidents/unresolved.json`\n- `/api/v2/components.json`\n\nNo API key, no auth, no rate-limit handling in the pack.\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"statuspage\": {\n      \"url\": \"https://gateway.pipeworx.io/statuspage/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/statuspage/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Statuspage data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 6398,
  "sha": "e7d14c6de4ba241853c5d22bf0b860b8ab5ea48a5dd542f580d036577f845504",
  "repo_slug": "pipeworx-io/mcp-statuspage",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_statuspage_872853af/readme"
}