About status-aggregator
status-aggregator is a stdio MCP server that consolidates status pages from SaaS providers used by AI agents. Its normalized status and incident data helps agents decide whether to retry or fall back.
Key features
- 01Aggregates status for 14+ SaaS providers
- 02Lists services and last-known status
- 03Gets provider details with status-page URL
- 04Shows active incidents today
- 05Summarizes overall service health
Use cases
- 01Decide whether to retry a failed request
- 02Choose a fallback based on service status
- 03Check the health of multiple dependencies
MCP support
It provides MCP clients with tools to list services, retrieve provider status, inspect active incidents, and get an overall health summary over stdio.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @weiseer/status-aggregator-mcpSTATUS_AGG_URLOverride remote snapshot URLSTATUS_AGG_LOCAL_ONLYSkip remote fetchLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
4Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| category | string | No | e.g. llm-provider, cloud, devtools, payments |
| current_status | string | No | e.g. operational, degraded, partial_outage, major_outage |
Details
From the project README@weiseer/status-aggregator-mcp
Cross-vendor SaaS status as a stdio MCP server. For AI agents deciding retry/fallback.
Probe P-003 by weiseer.
What it does
Aggregates the status pages of 14+ SaaS providers AI agents depend on (Anthropic, OpenAI, Google AI, Mistral, GitHub, npm, Cloudflare, AWS, Vercel, Netlify, Render, Stripe, Algolia, Linear) into one MCP server.
Your agent can:
list_services— list monitored providers + last-known statusget_status— full status for one provider with cited status-page URLget_incidents_today— active incidents across allcheck_all— quick health summary (counts by status)
Why use this instead of your agent fetching each status page
| Agent DIY (per call) | status-aggregator | |
|---|---|---|
| Status pages to fetch | 14 individual API calls | 1 MCP call |
| Token cost | $0.05-0.15 | $0 free / $0.00005 paid |
| Latency | 3-8 seconds | <100ms |
| Schema normalization | Per-vendor parsing | Pre-normalized |
Install
npm install -g @weiseer/status-aggregator-mcp
Use with Claude Desktop / Cursor / Cline / Continue / Windsurf
{
"mcpServers": {
"status-aggregator": {
"command": "npx",
"args": ["-y", "@weiseer/status-aggregator-mcp"]
}
}
}
Environment
STATUS_AGG_URL— override remote snapshot URLSTATUS_AGG_LOCAL_ONLY=1— skip remote fetch
Related weiseer services
@weiseer/llm-oracle-mcp— LLM pricing + availability oracle@weiseer/bounty-mcp— live coding-bounty deal-flow@weiseer/api-changelog-mcp— SDK breaking-change tracker- github.com/weiseer — all weiseer services
License
Apache-2.0
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.