agentrace MCP Server

by ura-tools Your server? Claim it

local only

agentrace runs on your own machine — the client starts it, so there is no endpoint to ping. 29 installs a week from npm.

Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.

Installs per day peak 9 · avg 4 · +107% w/w

a month agotoday

Installs / week

npm · @ura-dev/agentrace

—

Stars

on GitHub

—

Last commit

0 releases in 90 days

—

License

language unknown

Nothing serious here today

Today is the operative word: we check agentrace 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 agentrace -- npx -y @ura-dev/agentrace

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

{
  "mcpServers": {
    "agentrace": {
      "args": [
        "-y",
        "@ura-dev/agentrace"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.agentrace]
command = "npx"
args = ["-y", "@ura-dev/agentrace"]

.cursor/mcp.json

{
  "mcpServers": {
    "agentrace": {
      "args": [
        "-y",
        "@ura-dev/agentrace"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "agentrace": {
      "args": [
        "-y",
        "@ura-dev/agentrace"
      ],
      "command": "npx"
    }
  }
}

Alternatives to agentrace

same job, measured the same way

Langfuse

by pulsemcp

MCP server for Langfuse LLM observability — trace and observation analysis.

61 installs/wk local only

Spanly

by spanly

MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.

answering

Monitor

by betterdb-inc

BetterDB MCP server - Valkey observability for Claude Code and other MCP clients

92 installs/wk local only

Trace Forge

by mdfifty50-boop

Structured execution trace and span logging for AI agents

28 installs/wk local only

Agent Observability

by blueskylineassets

Agent observability: structured logging, cost tracking, and compliance audit trails

24 installs/wk local only

Mneme Decision MCP

by mnemehq

Local MCP server for architectural decisions, traceability, and non-authoritative proposals.

local only

MCP Agent Trace Inspector

by dbsectrainer

Step-by-step observability for MCP agent workflows

23 installs/wk local only

Sentry MCP

by getsentry

MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants

109 025 installs/wk local only

agentrace — questions

Answers built from our own checks of this server.

Why is there no uptime for agentrace?

agentrace 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 @ura-dev/agentrace was installed 29 times last week.

How do I connect agentrace?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @ura-dev/agentrace straight from npm; nothing to host, nothing to sign up for.

How many people use agentrace?

The npm package @ura-dev/agentrace was installed 29 times in the last week. Week over week that is +107%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.