MCP Agent Trace Inspector MCP Server

Step-by-step observability for MCP agent workflows

Remote serverstreamable-http

What is the MCP Agent Trace Inspector MCP server?

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.

What it actually does

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.

  • Tool call tracing — Captures inputs, outputs, latency, and token usage for every step in a workflow
  • Persistent storage — Traces survive session restarts; stored locally in SQLite with no external dependencies
  • HTML dashboard — Generates a self-contained single-file dashboard with an interactive step timeline
  • Token cost estimation — Calculates USD cost per trace using a configurable model pricing table — no API calls required
  • Trace comparison — Diff two traces side by side to measure the impact of prompt or tool changes
  • Low overhead — Adds less than 5ms per step; never becomes the bottleneck

Its toolset

Everything the assistant can do here goes through one of these:

  • 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)

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

  • Node.js v22.5.0 or newer. - npm.

When to reach for it

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.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP Agent Trace Inspector.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp agent trace inspector mcp server does with a few real requests.

Available tools

ToolWhat it does
trace_startbegin a new trace; returns a trace_id for subsequent calls
trace_steprecord one tool call step (inputs, outputs, optional token count and latency)
trace_endmark a trace as completed
list_traceslist stored traces with names, statuses, and timestamps
get_trace_summarytoken totals, step count, latency, and cost estimate for a trace
compare_tracesdiff two traces side by side (step counts, tokens, latency)
extract_reasoning_chainextract only reasoning/thinking steps from a trace
export_dashboardgenerate a self-contained single-file HTML dashboard with latency waterfall
export_otelexport one or all traces in OpenTelemetry OTLP JSON span format
export_compliance_logexport the compliance audit log as JSON or CSV, with optional date range filtering
configure_alertsconfigure alert rules on latency, error rate, or cost; fire to Slack or generic webhooks
set_retention_policyset how many days to keep traces (in-memory; must be called before apply_retention)
apply_retentionarchive traces older than the configured threshold; delete traces past 2x the threshold

How to install the MCP Agent Trace Inspector MCP server

{
  "mcpServers": {
    "trace-inspector": {
      "command": "npx",
      "args": ["-y", "mcp-agent-trace-inspector@latest"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js v22.5.0 or newer. - npm.

Example prompts to try

  • Use MCP Agent Trace Inspector to trace start.
  • Use MCP Agent Trace Inspector to trace step.
  • Use MCP Agent Trace Inspector to trace end.

Frequently asked questions

It connects MCP Agent Trace Inspector to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (trace_start, trace_step, trace_end, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Agent Trace Inspector directly.