API Status Check
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Live status probes plus published uptime and incident history for 280+ APIs and cloud services.
| Author | io.github.shibley |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 1967 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"API Status Check": {
"url": "https://apistatuscheck.com/api/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (8)
list_apisList the APIs and developer platforms this service monitors, optionally filtered by category. Statuses come from the most recently published monitor snapshot, not a live probe, and can be up to a day old — check monitorCheckedAt, and call get_api_status when the caller needs the status right now.
Parameters:
limit— integer — Max results (default 25).category— string — Category slug to filter by, e.g. "ai" — omit for all categories.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
search_apisFind monitored APIs by name, slug, category or description. Use this to resolve a product name the user mentioned into the slug the other tools take.
Parameters:
query(required) — string — Free-text query, e.g. "openai" or "payments".limit— integer — Max results (default 25).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_api_statusProbe a monitored API endpoint at call time and return up/degraded/down with the response time. This is the tool to reach for when a user asks "is X down?" — it makes a real request rather than reading the hourly cache.
Parameters:
slug(required) — string — API slug, e.g. "openai". Use search_apis to resolve a name.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_down_apisEverything the most recent monitor run found down or degraded, across all categories. Returns an empty list when the monitor snapshot is missing or stale — an empty list is therefore not proof that everything is healthy; check monitorLastRun.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_uptime_historyUptime percentages, response-time stats and recorded data points for one API over a time range. History is retained for 30 days; an API added recently will have few or no data points, which reads as null percentages rather than 100%.
Parameters:
slug(required) — string — API slug, e.g. "openai".range— string — Window to return data points for (default 24h).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_incident_historyReal incidents a vendor published on its own status page, newest first, with start/end times, duration, severity, affected components and a link to the vendor’s incident page. Use this for "has X been flaky lately?" — it is the vendor’s own record, not our probes. Services without a public Statuspage endpoint return covered:false rather than an empty list.
Parameters:
service(required) — string — API slug, e.g. "openai". Use search_apis to resolve a name.limit— integer — Max incidents (default 25).window— string — Time window: 7d, 30d, 90d, 180d, 365d, all (default 90d).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
rank_reliabilityGiven several service slugs, return a scorecard ranked worst-first: incident count, total downtime minutes, mean time to resolve, and the longest incident over a window. Use this to answer "which vendor in my stack is least reliable?" — it compares services across vendors, which a vendor’s own monitoring tool cannot. Services with no archive are listed separately as uncovered instead of being ranked as flawless.
Parameters:
services(required) — array — API slugs to compare, e.g. ["openai","anthropic","vercel"].window— string — Time window: 7d, 30d, 90d, 180d, 365d, all (default 90d).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_categoriesCategory slugs and how many monitored APIs sit in each. Use the slugs with list_apis.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.