MCP.Market

MCP Trace MCP server

by abhishekash·io.github.abhishekash/mcp-trace·v0.1.1
No reviews yet

Query OpenTelemetry traces from agent runs through MCP.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars261 downloads/wk

Reviews

Write one

Nobody has reviewed MCP Trace yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

MCP Trace tools (7, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • approval_log

    Human-in-the-loop audit: every approval/denial/edit, who decided, and the rationale.

  • list_runs

    List recent agent runs: task, model, duration, tool use, human decisions, cost.

  • run_summarywrite action

    Compact summary of one run (accepts trace_id prefix).

  • search_spans

    Substring search over span names/attributes, e.g. a tool name, file path, or 'denied'.

  • slowest_spans

    Top-k slowest spans. Use for 'why was this run slow?'. Omit trace_id to search all runs.

  • span_tree

    Nested span tree of a run — the shape of what the agent did, with durations.

  • token_usage

    Token and cost totals. Omit trace_id to aggregate across all runs.

Public scan report

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

no findings
  • Code scan6 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MCP Trace compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
7
the typical AI and agents server has 6
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
261
more than 78% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read · 1 run or deploy

Install MCP Trace in Claude Code, Cursor or VS Code

claude mcp add mcp-trace -- uvx abhishekash-mcp-trace
Add to Cursor

What the publisher says

From the MCP Trace repository's README, as published. We do not edit it. Read it on GitHub

mcp-trace-inspector

<!-- mcp-name: io.github.abhishekash/mcp-trace-inspector -->

Ask your agent what happened in a recorded local run. mcp-trace-inspector is a read-only stdio MCP server for inspecting local agent-run traces, including tool failures, approval decisions, and changes between runs. It reads JSONL spans in the format described in the user guide, including traces from agent-harness.

Demo: Watch the full 48-second video · Read the reproducible story. This is a scripted regression trace, not a live-model benchmark.

The project's concrete origin was a shell-boundary regression: the harness blocked cat ../outside.txt, but the old trace recorded only that run_shell was called, not the returned diagnostic. mcp-trace-inspector and the harness now preserve and query that bounded error.

Try the included trace

git clone https://github.com/abhishekash/mcp-trace-inspector.git
cd mcp-trace-inspector
uvx --from . mcp-trace-inspector --trace-dir examples --check

--check prints JSON with the trace directory, span count, and recent run summaries, then exits. It also reports a missing directory or malformed complete JSONL record. To ask questions through MCP, connect a client using the configuration below.

Release status: The 0.3.0 GitHub release is available. The PyPI

Trusted Publisher is configured; its first upload has not completed. Run the

tagged Git source with uvx below until uvx mcp-trace-inspector is available.

The MCP Registry entry

currently lists the earlier 0.2.2 package.

Publication status and directory submission handoff.

Where it fits

Use this when your agent already writes the supported JSONL span format and you want an MCP client to inspect those files without setting up a trace backend. Its focused queries include recorded approval decisions, bounded failure diagnostics, and comparisons between selected runs.

For traces stored in Jaeger, Tempo, or Traceloop, use a backend-connected tool such as OpenTelemetry MCP Server. For standard OTLP traces with a local receiver, see otel-mcp. For a trace UI, instrumentation, and evaluations, see Phoenix. This project does not ingest OTLP directly or read arbitrary OpenTelemetry JSON exports; other producers may need an adapter to the documented format.

AI-native use cases

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

MCP Trace: common questions

Is MCP Trace MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the MCP Trace safety report
How do I install MCP Trace?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does MCP Trace need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is MCP Trace maintained?
The last commit was 22 days ago (2026-10-13). The latest release is v0.1.1.
What can I use instead of MCP Trace?
Servers from other publishers that do the same job: IWE (iwe.md) MCP server, Superlog MCP server and Orcareplay MCP server.
How does MCP Trace compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to MCP Trace

Same job from other publishers: the closest match first, then the best rated.

  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Superlog
    Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
    A
  • Orcareplay
    Read, replay and fork recorded coding-agent runs.
    A

More from abhishekash →