Agenttrace MCP Server

by cloudcorprecords Your server? Claim it

local only

Agenttrace runs on your own machine — the client starts it, so there is no endpoint to ping. 222 installs a week from npm. Last commit 3 Nov 2026.

Summarize a supplied agent tool-call trace: per-tool stats, the error list, and totals.

Installs per day peak 189 · avg 7

a month agotoday

222

Installs / week

npm · @reneturcios/agenttrace

Stars

0 open issues

3 Nov 2026

Last commit

from GitHub

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Agenttrace every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agenttrace -- npx -y @reneturcios/agenttrace

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agenttrace": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/agenttrace"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.agenttrace]
command = "npx"
args = ["-y", "@reneturcios/agenttrace"]

.cursor/mcp.json

{
  "mcpServers": {
    "agenttrace": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/agenttrace"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agenttrace": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/agenttrace"
      ]
    }
  }
}

Alternatives to Agenttrace

same job, measured the same way

Agent Observability

by kryptosai

Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.

89 installs/wk local only

Agent Trace Check

by openkrill

Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.

4 tools answering

Talaria

by newtalaria

Errors, traces, replays and logs from Talaria for coding agents.

answering

ForgeOps

by getforgeops

Production errors and incidents for your agent: stack traces, breadcrumbs, likely causes, triage.

answering

MatLogica AADC: AAD, Greeks and the AADC Tracer

by matlogica

AAD from your coding agent: exact Greeks with MatLogica AADC, and a price traced to its source line

1 016 installs/wk local only

Stack Trace Medic

by evozim

Coded error stack trace debugger and automated patch generator.

1 tools answering

Flare

by flareapp

Error tracking for Laravel and PHP apps. Let your agent fetch errors, stack traces and context.

answering

Lore Context

by lore-context

Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.

34 installs/wk local only

Agenttrace — questions

Answers built from our own checks of this server.

Why is there no uptime for Agenttrace?

Agenttrace runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @reneturcios/agenttrace was installed 222 times last week.

How do I connect Agenttrace?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @reneturcios/agenttrace straight from npm; nothing to host, nothing to sign up for.

How many people use Agenttrace?

The npm package @reneturcios/agenttrace was installed 222 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agenttrace open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.