ai
Run Evaluation
Run model and agent evaluations against test cases and rubrics.
$1.435s96%
READ_DATA
Claude model capabilities for writing, coding, analysis, and agent workflows.
Trust
94/100
Reliability
96%
Latency
900ms
Usage
100,500
ai
Run model and agent evaluations against test cases and rubrics.
READ_DATA
{
"mcp_usage": {
"tool": "get_provider",
"input": {
"provider_slug": "anthropic"
},
"server": "https://anthropic.com/mcp",
"transport": "streamable_http"
},
"health_check": {
"status": "healthy",
"endpoint_reachable": true,
"manifest_valid": true
}
}