Agent Observability runs on your own machine — the client starts it, so there is no endpoint to ping. 177 installs a week from pypi. Last commit 25 Sep 2026.
AI agent observability with deterministic record/replay for debugging agent failures.
What the code does
We read the source, 18 h ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
return spawnSync(command, commandArgs, {
result = subprocess.run(command, env=env, check=False) # noqa: S603
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 agent-observability -- uvx agent-observability-trace-cli{
"mcpServers": {
"agent-observability": {
"args": [
"agent-observability-trace-cli"
],
"command": "uvx"
}
}
}[mcp_servers.agent-observability]
command = "uvx"
args = ["agent-observability-trace-cli"]{
"mcpServers": {
"agent-observability": {
"args": [
"agent-observability-trace-cli"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"agent-observability": {
"args": [
"agent-observability-trace-cli"
],
"command": "uvx"
}
}
}Alternatives to Agent Observability
same job, measured the same wayRecord and replay AI agent execution for debugging
Multi-agent observability: cascade failure detection, heartbeats, and forensic replay
eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging
Deterministic market-state engine for trading agents — state, gate, coordinates, with receipts.
Deterministic eligibility scoring for AI agents: CLEAR/HOLD/FAIL verdicts, published weights.
Deterministic authorization and security guard for AI agent actions with signed receipts.
AI-powered SRE observability for Kubernetes/OpenShift with 40+ Tekton debugging tools
Deterministic, read-only audits of repo readiness for AI coding agents and of agent context files.
Agent Observability — questions
Answers built from our own checks of this server.