Agent Trace Check in ChatGPT

Questions it answers

Agent Trace Check reads a tool-call log from an AI agent run and says what went wrong: which tools failed and how often, where the agent retried the same call in a loop, which calls it repeated with the same arguments, and which calls were slow.

Paste the log as JSON lines or one JSON value. It reads OpenAI chat messages with tool_calls, Responses API function_call items, Anthropic tool_use and tool_result blocks, Claude Code session JSONL files, MCP tools/call requests and their answers, LangSmith tool runs, OpenTelemetry tool spans, and flat rows with a tool name, arguments, a status or error, and a duration or timestamps.

Calls are paired with their results by id, or in order when the log has no ids. A call is slow at 10 seconds or more, or at 5 times its tool's median. A retry loop is 3 or more back-to-back calls to one tool where each repeats the last arguments or follows a failure. Both thresholds can be changed in one call.

The answer has findings ranked worst first, a table per tool with failures, median and slowest time and the most common error, and the lists of failures, retry loops, repeated calls and slow calls.

There is no account and nothing is stored. The log is read for the call and is not kept or cached, and no tool in it is called again. The only lasting record is a daily count of calls per tool.

What it can do

• Reads OpenAI, Anthropic, Claude Code, MCP, LangSmith, OpenTelemetry and flat JSON tool-call logs
• Pairs each tool call with its result by id, or in order when there are no ids
• Counts failures per tool and names the most common error
• Finds retry loops: back-to-back calls that repeat or follow a failure
• Finds the same call made again with the same arguments
• Lists slow calls by a fixed limit and by each tool's median time

Tools

• analyze_trace, Analyze an agent tool-call log. 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, Claude Code session JSONL, MCP JSON-RPC, LangSmith, OpenTelemetry spans, or flat rows with tool, args, status or error and duration_ms. Returns findings worst first, per-tool stats, failures, retry loops, repeated calls and slow calls. Nothing is stored. It does not run the agent or any tool.

Add Agent Trace Check in ChatGPT

ChatGPT does not read a local config file. A custom MCP server is added in the product, and only after developer mode is on. These steps were checked against OpenAI's plugin connect guide and the ChatGPT MCP guide on 2026-10-01. Developer mode can be hidden by a workspace policy, so a Team or Enterprise admin may have to allow it first.

1. Open ChatGPT settings, then Security and login, and turn on Developer mode.
2. Open ChatGPT plugins and select the plus button.
3. Enter a name such as "Agent Trace Check" and a one-line description of what you want it to answer.
4. Under Connection, choose the public endpoint and paste https://agenttrace.openkrill.app/mcp. Include the /mcp path. Do not add a tunnel id: this server is already public.
5. Create the connection and review the tools ChatGPT lists. You should see analyze_trace. The feedback tools on the same server are optional and not required for the lookup.
6. Start a new conversation, add the connection from the tools menu, and ask: Analyze this agent tool-call log and tell me why the run failed.

No API key and no OAuth client id are required. The server answers without a login. Calls are limited per network and per day, and a limit comes back as a tool error rather than a partial answer. If the tool list is stale after a server change, open the connection and select Refresh, then start a new conversation.

The ChatGPT desktop app, Codex CLI and IDE extension share a different config. In the desktop app, open Settings, then MCP servers, choose Add server, select Streamable HTTP, and paste the same URL. In ~/.codex/config.toml the equivalent is a table named mcp_servers.agent-trace with url = "https://agenttrace.openkrill.app/mcp". ChatGPT on the web does not read that file. A published directory listing is also a different path: this page is the developer-mode connection, not a claim that Agent Trace Check is already in the ChatGPT directory.

Treat the server as untrusted until you have read a few answers. A remote MCP server sees the arguments the model sends. Agent Trace Check is read-only and documents what it sends onward on the privacy page.

If it does not work

A call checked on 2026-10-11

Four made-up log rows: one fetch that timed out 3 times in a row, then a search that worked. The tool reads only this text and calls nothing. The request below was posted to https://agenttrace.openkrill.app/mcp as tools/call. HTTP 200. Source: the Agent Trace Check server, read 2026-10-11.

{
  "method": "tools/call",
  "params": {
    "name": "analyze_trace",
    "arguments": {
      "trace": "{\"tool\":\"web_fetch\",\"args\":{\"url\":\"https://example.com/a\"},\"status\":\"error\",\"error\":\"timeout after 30000 ms\",\"duration_ms\":30000}\n{\"tool\":\"web_fetch\",\"args\":{\"url\":\"https://example.com/a\"},\"status\":\"error\",\"error\":\"timeout after 30000 ms\",\"duration_ms\":30000}\n{\"tool\":\"web_fetch\",\"args\":{\"url\":\"https://example.com/a\"},\"status\":\"error\",\"error\":\"timeout after 30000 ms\",\"duration_ms\":30000}\n{\"tool\":\"search\",\"args\":{\"q\":\"example\"},\"status\":\"ok\",\"duration_ms\":800}"
    }
  }
}

• notice. Computed from the pasted log alone. Nothing was stored, and no tool in the log was called again. Calls are matched by id, or in order when the log has no ids.
• findings. 3 returned
• by tool. 2 returned
• failures. 3 returned
• retry loops. 1 returned
• repeated calls. 1 returned

Repeat the call yourself if you need a newer reading. Cached answers expire. A rate limit is not a result: wait and try again. Nothing in the call is a ranking, a filing, or advice.

Using it in production

Nothing to install and nothing to run: no package, no Python or Node.js version and no environment variable. Agent Trace Check runs on our servers, and your client only needs the URL https://agenttrace.openkrill.app/mcp.

Use it in other apps

• Agent Trace Check in Claude
• Agent Trace Check in Cursor
• Agent Trace Check in VS Code
• Agent Trace Check in Pi

Frequently asked questions

Words on this page

• MCP (Model Context Protocol) definition
• Streamable HTTP transport definition
• Tool primitive definition
• Rate limit policy definition

Source: plugin listing for agent-trace in this repository, and a live tools/call on 2026-10-11. As of 2026-10-11.