Agentic Observability MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 36 installs a week from npm. Last commit 24 Apr 2026.
Agent tracing, cost tracking, anomaly detection for LLM agents
Today is the operative word: we check Agentic Observability MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agentic-observability -- npx -y agentic-observability-mcp
{
"mcpServers": {
"agentic-observability": {
"args": [
"-y",
"agentic-observability-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agentic-observability]
command = "npx"
args = ["-y", "agentic-observability-mcp"]
{
"mcpServers": {
"agentic-observability": {
"args": [
"-y",
"agentic-observability-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentic-observability": {
"args": [
"-y",
"agentic-observability-mcp"
],
"command": "npx"
}
}
}
Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.
MCP server for Langfuse LLM observability — trace and observation analysis.
LLM Observability & Orchestration Agent
LLM Orchestration Observability Agent
Agent observability: structured logging, cost tracking, and compliance audit trails
Canonical Agentry discovery for coding agents: analytics, errors, deploys, and automation.
Multi-agent observability: cascade failure detection, heartbeats, and forensic replay
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
Answers built from our own checks of this server.