MCP server

Agent Trace Check

app.openkrill/agent-trace

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

openkrill.app (verified by the MCP Registry)

Status

Working at last check

Tools

4

Token cost

About 1,295 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http agent-trace https://agenttrace.openkrill.app/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.agent-trace]
url = "https://agenttrace.openkrill.app/mcp"

Gemini CLI

{"mcpServers":{"agent-trace":{"httpUrl":"https://agenttrace.openkrill.app/mcp"}}}

Cursor

{"mcpServers":{"agent-trace":{"url":"https://agenttrace.openkrill.app/mcp"}}}

VS Code

{"servers":{"agent-trace":{"type":"http","url":"https://agenttrace.openkrill.app/mcp"}}}

Antigravity

agy mcp add agent-trace https://agenttrace.openkrill.app/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"agent-trace","server_url":"https://agenttrace.openkrill.app/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"agent-trace","server_url":"https://agenttrace.openkrill.app/mcp"}

Tools

• analyze_trace ~494 tokens
  Use this when the user pastes a log of an AI agent's tool calls and wants to know which calls failed, where the agent retried in a loop, which calls it repeated, or which were slow. Pass the log as trace: JSON lines or one JSON value from OpenAI messages, the Responses API, Anthropic messages, Claud

Browse

• Claude tools
• Calling other AI models

Related MCP servers

• Snapback
  Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.
• Phpray
  Ask an agent why a PHP site is slow: every request with its SQL, HTTP calls, errors and N+1.
• Agent Loop Detector
  Cloudflare Workers MCP server: agent-loop-detector
• Loop Breaker
  Catch AI agent loops: halt runs that repeat the same failing step or tool call.
• Agent Trace Auditor
  Cloudflare Workers MCP server: agent-trace-auditor
• Diogenes Agent Guardrails & Sandbox MCP
  Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
• Code Auditor
  Enforces architectural invariants and code quality rules inside your AI agent's edit loop.
• Pixfaro
  Generate images with any major model — one API key, one prepaid balance, one MCP.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/app.openkrill/agent-trace.svg)](https://aptlynx.net/servers/app.openkrill/agent-trace)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents