AgentStatus
We tested every public MCP server we could find. Calling is solved. Delivery is not.
Read the reportAgent marketplaces are booming.
Platforms listing thousands of agents. Developers publishing their creations. Users browsing, selecting, deploying.
There's just one problem: research shows 95% of AI agents failed to meet production requirements in 2025 (vaza.ai). How do you know which ones actually work?
App stores solved trust with:
These work reasonably well. A 4.5-star app with 100K downloads is probably decent.
These signals break down:
Reviews don't work:
Downloads don't work:
Verification is insufficient:
Curation doesn't scale:
An agent was built on GPT-3.5-turbo-0301. Worked great.
Model deprecated. Agent now uses fallback model. Behavior completely different.
Marketplace still lists it. Reviews from 6 months ago say it's great. Current users get broken behavior.
Agent calls external APIs. Free tier API key.
First 1000 users/day: works perfectly. User 1001+: rate limited, returns errors.
Marketplace shows 5-star reviews from the first 1000. Everyone else sees failures.
Agent hosted on a single US server.
US users: great performance. Asia users: 5+ second latency, frequent timeouts.
Marketplace has no geographic data. Asian users have no warning.
Agent quality slowly declines over 3 months.
Original reviews: "Incredible! Best code assistant ever!" Current behavior: Generic, often wrong suggestions.
Nothing triggers a warning. Reviews persist. New users disappointed.
Not reviews from 6 months ago. Live health status.
Agent: CodeAssistant Pro
Status: UP ✓
Uptime (24h): 99.2%
Last Check: 2 minutes agoUsers see what's happening now, not what happened to someone else before.
Show performance by region.
US: ✓ Fast (420ms P50)
EU: ✓ Good (890ms P50)
Asia: ⚠️ Slow (2400ms P50)Users know before they deploy: "This agent won't work well for my Asian users."
Not just "runs" but "works correctly."
Gold Prompt Pass Rate: 97%
Contract Compliance: 95%Quantified quality, not just vibes.
Is it getting better or worse?
Quality Trend (30d): ↘️ Declining
Latency Trend (30d): ↗️ IncreasingCatch degradation before you deploy.
We provide the trust infrastructure that marketplaces need.
For Marketplace Operators:
# Batch status for all listed agents
GET /api/agentstatus/status?agent_ids=id1,id2,id3,id4,...
{
"agents": {
"id1": {"status": "UP", "uptime_24h": 99.8, "latency_p50": 450},
"id2": {"status": "DOWN", "uptime_24h": 45.2, "latency_p50": null},
"id3": {"status": "DEGRADED", "uptime_24h": 92.1, "latency_p50": 3200}
}
}Display this data on agent cards. Users see real-time reliability.
For Agent Developers:
<!-- Agent Status Verified Badge -->
<img src="https://api.fabric.carmel.so/api/agentstatus/agents/abc123/badge"
alt="Agent Status Verified: 99.2% Uptime" />Earn trust with continuous validation. Stand out from unverified competitors.
Marketplaces can compute trust scores:
def compute_trust_score(agent_id):
data = agentstatus.get_history(agent_id, days=30)
uptime_score = data.uptime * 0.35 # 35% weight
latency_score = normalize(data.latency) * 0.25 # 25% weight
gold_score = data.gold_pass_rate * 0.30 # 30% weight
consistency_score = 1 - data.variance * 0.10 # 10% weight
return sum([uptime_score, latency_score, gold_score, consistency_score])Trust Grade: A (90-100), B (80-89), C (70-79), D (below 70).
For platforms that route to multiple agents:
async def select_agent(query, candidates):
# Get live status for candidates
statuses = await agentstatus.batch_status([c.id for c in candidates])
# Filter to healthy agents
healthy = [c for c in candidates if statuses[c.id].status == "UP"]
if not healthy:
raise NoHealthyAgents()
# Select fastest among healthy
return min(healthy, key=lambda c: statuses[c.id].latency_p50)Don't route to broken agents. It's that simple.
Nasiko (agent registry) is integrating Agent Status for exactly this problem.
Before:
After:
Result: Users trust the marketplace more. Reliable agents get more usage. Bad agents surface quickly. Overall ecosystem quality improves.
Beyond real-time status, marketplaces can offer certification:
If an agent falls below standards:
This maintains badge credibility.
Agent Status's free tier is sufficient for basic verification. Paid tiers provide more frequent checks and more regions.
This creates a virtuous cycle:
Everyone wins. Except the agents that don't work.