Agent Observability runs on your own machine — the client starts it, so there is no endpoint to ping. 80 installs a week from npm. Last commit 28 Jul 2026.
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
What the code does
We read the source, 4 d ago · rules 995398eba69f
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.
postinstall: node scripts/postinstall.mjs || true
const child = spawn(targetCommand, targetArgs || [], {
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 -- npx -y agent-obs{
"mcpServers": {
"agent-observability": {
"command": "npx",
"args": [
"-y",
"agent-obs"
]
}
}
}[mcp_servers.agent-observability]
command = "npx"
args = ["-y", "agent-obs"]{
"mcpServers": {
"agent-observability": {
"command": "npx",
"args": [
"-y",
"agent-obs"
]
}
}
}{
"servers": {
"agent-observability": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-obs"
]
}
}
}Alternatives to Agent Observability
same job, measured the same wayPre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Structured execution trace and span logging for AI agents
Local-first, source-traceable agent memory — no LLM at ingest, fully offline
Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.
Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
Local-first PHI detection for source code, LLM prompts, logs, and analytics
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Agent Observability — questions
Answers built from our own checks of this server.