kyde score is answering right now. Last checked 8 min ago. It exposes 6 tools.
Agent observability via OpenTelemetry: drift, loop and hijack alerts, e.g. after a prompt injection.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 3 November 2026. No other catalogue keeps this.
Today is the operative word: we check kyde score every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add score --transport http https://score.kyde.com/mcp
https://score.kyde.com/mcp
[mcp_servers.score]
url = "https://score.kyde.com/mcp"
{
"mcpServers": {
"score": {
"url": "https://score.kyde.com/mcp"
}
}
}
{
"servers": {
"score": {
"type": "http",
"url": "https://score.kyde.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
claim_key
create_key
rebaseline
revoke_key
get_scores
set_webhook
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://score.kyde.com/mcp | streamable-http | answering | 157 ms | 8 min ago |
AI agent observability for production traces, natural-language insights, and improvement loops.
lu.ma events MCP server with draft+confirm safety, audit logging, and prompt-injection scrubbing.…
Data observability: alerts, freshness checks and schema drift for your data assets.
Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.
Observability for incident agents — query Loki (LogQL), Prometheus (PromQL), Elasticsearch.
Manage Sable AI voice agents, query HyperDX logs and metrics, and deploy — all from your IDE
Data + AI observability — monitor and troubleshoot production-grade agents and the context they use.
Production telemetry for NestJS apps: traces, errors, regressions, jobs and alerts.
Answers built from our own checks of this server.