AgentStatus
We tested every public MCP server we could find. Calling is solved. Delivery is not.
Read the reportTrue story: A team's agent worked perfectly for six months. Then they expanded to Asia.
Support tickets from Singapore users started rolling in. The agent was "slow" or "unresponsive." Engineers couldn't reproduce it from their San Francisco office.
The agent worked perfectly from SF. It was nearly unusable from Singapore.
Their monitoring showed 99.9% uptime. Because their monitoring only checked from US data centers.
Let's start with basics.
Speed of light: ~300,000 km/s
SF to Singapore: ~13,500 km
Minimum round trip: ~90ms (just physics)
Add in:
Real-world SF → Singapore latency: 200-500ms just to establish connection.
Now add your agent's inference time on top.
An agent that responds in 1 second from SF takes 1.5-2 seconds from Singapore. That's the best case.
Traditional monitoring architecture:
[Your US Server] ←→ [Monitoring from US Datacenter]
↓
"100% uptime!"This tests: "Does our agent work from a nearby, well-connected data center?"
It doesn't test: "Does our agent work for actual users?"
Your users aren't in data centers. They're on:
Your CDN has points of presence (POPs) worldwide. Each is independently configured.
Failure: Singapore POP has stale cache or misconfiguration.
Result: Works in US, fails in Singapore.
Your US monitoring sees: Nothing.
You update DNS. It propagates at different speeds globally.
Failure: Asia-Pacific DNS servers still have old record.
Result: Works in US (new IP), fails in APAC (old IP).
Your US monitoring sees: Nothing.
Some ISPs have poor peering with your hosting provider.
Failure: NTT (major Asian ISP) routes your traffic through congested path.
Result: Works for 90% of users, fails for users on NTT.
Your US monitoring sees: Nothing.
Some providers apply rate limits by region.
Failure: You hit OpenAI's regional rate limit for European IP ranges.
Result: Works in US, rate limited in EU.
Your US monitoring sees: Nothing.
Firewall rules or WAF configurations can block by geography.
Failure: Security rule accidentally blocks Asian IP ranges.
Result: Works everywhere except Asia.
Your US monitoring sees: Nothing.
Geographic latency is not just a convenience issue-it directly impacts reliability.
The HB-Eval research shows that agents are sensitive to perturbations, dropping from 86.9% to 44.0% success rates under stress. Network latency adds timeout pressure that compounds these failure modes.
Example latency progression (US-hosted agent):
| Region | Base Latency | With LLM Inference | User Experience |
|---|---|---|---|
| US East | ~50ms | ~1-2s total | Acceptable |
| US West | ~100ms | ~1.5-2.5s total | Acceptable |
| EU | ~150-200ms | ~2-3s total | Noticeable |
| APAC | ~200-300ms | ~3-5s total | Frustrating |
| Africa | ~300-400ms | ~4-6s total | Often timeouts |
Key insight: As latency increases, timeout rates increase-and when agents face network perturbations, their already-stressed architectures fail more frequently.
When regional issues occur, how long until detection?
| Monitoring Type | Detection Time |
|---|---|
| Single-location monitoring | Hours to days (customer report) |
| Geographic monitoring | <15 minutes |
The difference is whether you find it or your users do.
Data center IPs often get special treatment at the edge:
Residential IPs (actual user connections) experience:
Testing from data centers often measures a different access surface — whether the edge lets the probe in, and what latency the path shows. It does not relocate the agent's outbound tools. For reachability, geo-block, and client-IP locale branches, residential vantage is the honest observer. For stably wrong answers after HTTP 200, you still need semantic evaluation.
{
"overall_verdict": "DEGRADED",
"by_region": {
"us": {"status": "UP", "ttfb_p50": 420, "pass_rate": 100},
"eu": {"status": "UP", "ttfb_p50": 890, "pass_rate": 98},
"apac": {"status": "DOWN", "ttfb_p50": null, "pass_rate": 15}
}
}Immediately clear: US and EU are fine, APAC is broken.
For agents that should give location-aware responses (weather, local info, search):
[User location: Singapore]
What's the weather like today?We prepend the test's location to verify whether your agent gives appropriate regional responses.
Pattern:
Cause: No edge deployment. All traffic routes to origin.
Fix: CDN, edge caching, or regional deployment.
Pattern:
Cause: Regional infrastructure issue (CDN edge, DNS, routing).
Fix: Investigate that specific region's infrastructure.
Pattern:
Cause: Capacity issues, rate limiting, or network instability.
Fix: Increase capacity, review rate limits, add redundancy.
Pattern:
Cause: Growing traffic, degrading infrastructure, or routing changes.
Fix: Capacity planning, infrastructure review.
Not where your servers are. Not where your office is. Where your users are.
If 30% of users are in EU, have 30% of monitoring from EU.
Different regions may have different acceptable thresholds:
| Region | Max TTFB | Min Pass Rate |
|---|---|---|
| US | 2s | 95% |
| EU | 3s | 90% |
| APAC | 5s | 85% |
Be realistic about physics.
Don't just alert on global DOWN. Alert when specific regions degrade.
Data center checks are supplementary. Residential checks are primary.
A region getting slowly worse is a signal to investigate before it becomes an outage.
Cost of regional monitoring: ~$20/month for global coverage.
Cost of 12-hour regional outage discovered by customer complaints:
The math isn't close.