Step-by-step observability for MCP agent workflows
Step-by-step observability for MCP agent workflows. Exposed over MCP by the mcp agent trace inspector mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
Local-first, MCP-native observability for agent workflows. Every tool call, prompt transformation, latency, and token count is recorded in a local SQLite database — no cloud account, no API key, no traces leaving your machine. Built specifically for MCP rather than bolted onto a generic LLM proxy.
Everything the assistant can do here goes through one of these:
trace_start — begin a new trace; returns a trace_id for subsequent callstrace_step — record one tool call step (inputs, outputs, optional token count and latency)trace_end — mark a trace as completedlist_traces — list stored traces with names, statuses, and timestampsget_trace_summary — token totals, step count, latency, and cost estimate for a tracecompare_traces — diff two traces side by side (step counts, tokens, latency)extract_reasoning_chain — extract only reasoning/thinking steps from a traceexport_dashboard — generate a self-contained single-file HTML dashboard with latency waterfallexport_otel — export one or all traces in OpenTelemetry OTLP JSON span formatexport_compliance_log — export the compliance audit log as JSON or CSV, with optional date range filteringconfigure_alerts — configure alert rules on latency, error rate, or cost; fire to Slack or generic webhooksset_retention_policy — set how many days to keep traces (in-memory; must be called before apply_retention)Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP Agent Trace Inspector's toolset — trace_start, trace_step, trace_end and 10 more — is a fair guide to whether it matches your workflow. It is maintained by dbsectrainer; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| trace_start | begin a new trace; returns a trace_id for subsequent calls |
| trace_step | record one tool call step (inputs, outputs, optional token count and latency) |
| trace_end | mark a trace as completed |
| list_traces | list stored traces with names, statuses, and timestamps |
| get_trace_summary | token totals, step count, latency, and cost estimate for a trace |
| compare_traces | diff two traces side by side (step counts, tokens, latency) |
| extract_reasoning_chain | extract only reasoning/thinking steps from a trace |
| export_dashboard | generate a self-contained single-file HTML dashboard with latency waterfall |
| export_otel | export one or all traces in OpenTelemetry OTLP JSON span format |
| export_compliance_log | export the compliance audit log as JSON or CSV, with optional date range filtering |
| configure_alerts | configure alert rules on latency, error rate, or cost; fire to Slack or generic webhooks |
| set_retention_policy | set how many days to keep traces (in-memory; must be called before apply_retention) |
| apply_retention | archive traces older than the configured threshold; delete traces past 2x the threshold |
{
"mcpServers": {
"trace-inspector": {
"command": "npx",
"args": ["-y", "mcp-agent-trace-inspector@latest"]
}
}
}Configuration as documented by the project. Restart the client after saving.
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.