mcp-trace-inspector

Read local agent-run JSONL traces through MCP for failures, approvals, and run comparisons.

Connector by abhishekash · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/abhishekash-mcp-trace-inspector

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Read local agent-run JSONL traces through MCP for failures, approvals, and run comparisons.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools: 7 read · 1 write · 0 delete · 4 not yet classified
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Tools by what they do 12

Read from the source code; the running server may list different tools.

Read 7 · Look things up without changing anything.

compare_runs
failure_report
list_runs
recent_activity
search_spans
security_audit
tool_stats

Write 1 · Create, change, send or run things.

run_summary

Not yet classified 4 · We could not tell from the name and description.

approval_log
slowest_spans
span_tree
token_usage

Network hosts it talks to 2

github.com · found in code
glama.ai · found in code

Files it touches

/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf
/usr/share/fonts/truetype/dejavu/DejaVuSansMono.ttf

Tools (12)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

approval_log
Human-in-the-loop audit: every approval/denial/edit, who decided, and the rationale. Use when asked 'why did the agent get to do X?' or 'what was denied?'.
compare_runs
Compare selected trace-id prefixes for latency, cost, tokens, tools, and failures.
failure_report
Show bounded, redacted tool/provider failures and their actionable diagnostics.
list_runs
List recent agent runs: task, model, duration, tool use, human decisions, cost. Use first to find the trace_id for deeper inspection.
recent_activity
Poll newly written spans using a cursor; useful while an agent run is still active.
run_summary
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'.
security_audit
Audit caller identity, tenant, server provenance, risk, and approval evidence for tool calls.
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.
tool_stats
Rank tools by errors, denials, latency, and call volume to find unhealthy integrations.

Signals

Stars: 1
Forks: 0
Open issues: 0
Weekly downloads: 41
Last commit: Oct 17, 2026 (13 days ago)
Last release: Oct 15, 2026 (14 days ago)
Last package publish: Oct 13, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.abhishekash/mcp-trace-inspector
Version: 0.3.1
Auth: No auth
Packages: pypi mcp-trace-inspector
License: MIT
Repository: github.com/abhishekash/mcp-trace-inspector
First seen: Oct 24, 2026
Last checked: Oct 25, 2026
Source: Official MCP Registry github-graphql

More from abhishekash

Cite this page

mcp-trace-inspector. Agent Mart. https://agentmart.dev/connectors/abhishekash-mcp-trace-inspector (last updated 2026-10-25)