Cursor + TraceBug (MCP)

Cursor bug reports:
capture it, let Cursor fix it

Cursor can fix a bug it can actually see. TraceBug captures the browser session — replay, console errors, the failed request, the exact repro steps — into one file Cursor reads over a local MCP server, then reproduces and fixes it. Nothing is uploaded.

Watch AI fix a real bug Cursor setup guide

Connect TraceBug to Cursor

Cursor reads MCP servers from a JSON config — project-level or global. Add the tracebug entry, enable it in Settings → MCP, and Cursor's Agent mode can read every TraceBug export on your machine.

.cursor/mcp.json (project) or ~/.cursor/mcp.json (global)
{
  "mcpServers": {
    "tracebug": {
      "command": "npx",
      "args": ["-y", "tracebug", "mcp"]
    }
  }
}

Full walkthrough with troubleshooting: the Cursor MCP setup guide.

What Cursor reads from the report

The local server gives Cursor read-tools over the captured evidence — console errors with stack traces, the failing network request and its response body, the millisecond repro timeline, and screenshots. It starts from the actual failing line instead of guessing from a description.

From root cause to a verified fix

Every report also embeds a generated failing test that replays the session and asserts the failure is gone. Cursor runs it (red), patches the code, and re-runs until green — so the fix is verified, not just proposed.

Capture → Cursor reads the evidence → fix → the test goes green.

Local, not cloud. The MCP server runs on your machine over stdio with zero network connections; the report is one offline file and secrets are masked at capture. Your bug data and your code never leave your machine. MIT open source.

See Cursor fix a real bug
Unedited transcript: crash → root cause → verified fix.
Watch the proof