62trust / 100

Fittest

by fittest-mcp.westus2.cloudapp.azure.com in Developer tools

MCP serverFailing, checked 10 h ago

Three ML interatomic potentials check a molecule: trust (Beta-posterior score, 90% CI) or DFT.

https://fittest-mcp.westus2.cloudapp.azure.com/mcp
Tools
4
open to any client
Uptime
33.3%
last 30 days
Response time
600 ms
822 ms slowest 5%
Last check
Failed
10 h ago, next in 12 h

Scan it nowHow to connect

Reliability

All checks passedSome failedAll failedNot checked

Latest check failed 10 h ago: Timed out

Status and outage history · Atom feed · Watch with other listings

How to connect

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "fittest": {
      "type": "http",
      "url": "https://fittest-mcp.westus2.cloudapp.azure.com/mcp"
    }
  }
}

4 tools

  • check_structures

    Ask the Fittest swarm whether a machine-learned interatomic potential can be trusted on your molecular structures, or whether they need DFT. Three model agents (MACE-MPA-0, AIMNet2, Orb-v3) predict forces; their disagreement sigma_F and the Calibrator's DFT-label ledger give the…

  • explain

    Explain why Fittest trusted or escalated ONE structure (XYZ text or {Z|symbols, R}): the verdict rule applied, sigma_F vs tau, the Calibrator bucket with its label count, the posterior P(correct) of every candidate in it, which model agents disagree most, and the most uncertain…

  • swarm_status

    Show the Fittest population: model agents (answerers) and the Skeptic (critic) with reputations from the ledger, the calibration domain, tau and the verdict rule, which models are live, and the evolution family trees if published. Logging: every call to this server is logged…

  • usage_stats

    Aggregate usage of this server: distinct users (anonymous clients that got at least one structure verdict; internal test clients excluded), total calls, calls per tool, first/last call time. No per-user data. Logging: every call to this server is logged (UTC time, tool name, an…

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
10 h agoTimed out--
38 h agoTimed out--
3 days agoTimed out--
4 days agoTimed out--
5 days agoTimed out--
Show 7 older checks
6 days agoTimed out--
7 days agoTimed out--
8 days agoTimed out--
8 days agoPassed200822 ms
9 days agoPassed200600 ms
9 days agoPassed200599 ms
10 days agoPassed200628 ms