Skip to main content
Glama

Independent AI API uptime

get_uptime
Read-onlyIdempotent

Uptime and latency of ~24 public AI API hosts (OpenAI, Anthropic, Google Gemini, Mistral, xAI, DeepSeek, Groq, Together, Fireworks, OpenRouter, Cohere, ElevenLabs, AWS Bedrock and more), measured by InfraRabbit itself every 5 minutes, not reported by the provider. Without host: every host with its current state and uptime %, p50 and p95 latency for the last 24 h, 7 d and 30 d. With host (the hostname, e.g. api.openai.com): its daily rows for days days and its incidents (two or more consecutive down windows, with start, end and evidence). Method: one unauthenticated HTTPS GET per host per round (DNS, TCP, TLS, time to first byte, HTTP status), from one vantage. It proves the provider's edge or gateway answered from there; it does NOT prove that a model generates or that your key, quota or region works. Check coverage_pct before quoting a figure: it says how much of the window was measured. Returns an error object for an unknown host. Same data as GET /v1/uptime and /v1/uptime/{host}/history and the page /prices/uptime.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_uptime"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoDays of daily rows and incidents when a host is given, 1 to 365
hostNoHostname as listed by this tool without a host, e.g. api.openai.com. Omit for every host.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the bar is low — yet the description adds substantial context: 5-minute cadence, one vantage, exact probe method (DNS, TCP, TLS, TTFB, HTTP status), the incidents definition (two or more consecutive down windows with start/end/evidence), the coverage_pct caveat, and error behavior for an unknown host. This is exactly the honest-limits framing an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and provider list, then mode behavior, then caveats — every sentence carries information. It is a single dense paragraph rather than segmented, which slightly hurts scannability for a definition of this length, but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by naming the returned fields and structures (current state, uptime %, p50/p95 over 24h/7d/30d, daily rows, incidents with evidence, coverage_pct, error object). For a two-param read-only monitoring tool, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented, but the description adds conditional semantics the schema lacks: `days` only takes effect when `host` is supplied, and `host` must be a hostname as listed by the no-host call. That conditional coupling is genuine value beyond the JSON schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (uptime and latency of ~24 named public AI API hosts) and immediately scopes the two modes: without `host` returns all hosts with current state and uptime %, with `host` returns daily rows plus incidents. The list of providers and the independence claim ('measured by InfraRabbit itself... not reported by the provider') make it unmistakable from the pricing/change siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The with/without `host` branching gives clear calling context, and it adds a practical rule ('Check coverage_pct before quoting a figure') plus an explicit statement of what the data does not prove. It stops short of naming when to prefer a sibling such as get_history, so an agent must infer that itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources