MCP Agent Trace Inspector runs on your own machine — the client starts it, so there is no endpoint to ping. 23 installs a week from npm. Last commit 24 Mar 2026.
Step-by-step observability for MCP agent workflows
Today is the operative word: we check MCP Agent Trace Inspector 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 mcp-agent-trace-inspector -- npx -y mcp-agent-trace-inspector
{
"mcpServers": {
"mcp-agent-trace-inspector": {
"args": [
"-y",
"mcp-agent-trace-inspector"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-agent-trace-inspector]
command = "npx"
args = ["-y", "mcp-agent-trace-inspector"]
{
"mcpServers": {
"mcp-agent-trace-inspector": {
"args": [
"-y",
"mcp-agent-trace-inspector"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-agent-trace-inspector": {
"args": [
"-y",
"mcp-agent-trace-inspector"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
YOUR_API_KEY (Your API key for the service).
The author declared them in the registry entry; get the values from the project itself.
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
BetterDB MCP server - Valkey observability for Claude Code and other MCP clients
MCP server for Langfuse LLM observability — trace and observation analysis.
MCP server for Alert Logic MDR — incident response, log search, SOAR, and SOC workflows
Observability for incident agents — query Loki (LogQL), Prometheus (PromQL), Elasticsearch.
MCP server for Prefect. Monitor and debug workflows, deployments, and automations.
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
MCP server for querying logs from observability platforms with unified search and tracing
Answers built from our own checks of this server.