Documentation Index
Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt
Use this file to discover all available pages before exploring further.
Trace Cursor IDE and CLI conversations, shell commands, MCP tools, and file operations in Arize AX for full observability.Cursor is an AI code editor for agentic software development. The Arize Coding Harness Tracing instruments Cursor IDE and CLI hook events and exports OpenInference spans to Arize AX or Phoenix. A Cursor conversation maps to a session, and each message turn maps to a trace.
Launch Arize AX
To get started, sign up for a free Arize AX account and get your Space ID and API Key:- Log in at app.arize.com
- Click Settings and copy the Space ID
- Open the API Keys tab and create or copy an API key
Install
Curl installer
macOS / Linux:Local clone
~/.arize/harness/config.yaml, and registers the hooks in ~/.cursor/hooks.json. Both Cursor IDE and Cursor CLI sessions are instrumented from the same configuration.
Configuration
Credentials live in~/.arize/harness/config.yaml. Environment variables override values in config.yaml and can be set in your shell profile so they apply to Cursor IDE and Cursor CLI sessions.
Phoenix (self-hosted)
Arize AX (cloud)
Redaction controls
EachARIZE_LOG_* flag accepts "true" or "false" and defaults to "true". Set to "false" to opt out per category:
| Flag | Redacts |
|---|---|
ARIZE_LOG_PROMPTS | User prompt and assistant response text |
ARIZE_LOG_TOOL_DETAILS | Tool names and arguments |
ARIZE_LOG_TOOL_CONTENT | Tool call output content (shell output, MCP results, file contents) |
Observe
Once tracing is enabled, Cursor activity is streamed to Arize AX. You’ll see:- Session grouping by
conversation_idfor each Cursor conversation - Turn traces by
generation_idfor each message turn - User prompt spans for submitted prompts
- Agent response spans with model output
- Agent thinking spans when Cursor emits reasoning/thought events
- Shell spans with command input and command output merged into a single tool span
- MCP spans named
MCP: {tool}with tool input and result - File read and edit spans for file operations, including tab reads and edits
cursor unless you set ARIZE_PROJECT_NAME.
Hooks Captured
Cursor IDE fires the full set of hooks. Cursor CLI fires a subset (no prompt/response, MCP, or file-read events).| Hook | IDE | CLI | Captured Data |
|---|---|---|---|
sessionStart | ✓ | ✓ | Session boundary, state init |
sessionEnd | ✓ | ✓ | Session teardown |
beforeSubmitPrompt | ✓ | User prompt span for the turn root | |
afterAgentResponse | ✓ | Agent response text and model metadata | |
afterAgentThought | ✓ | Agent thinking output and duration | |
beforeShellExecution | ✓ | ✓ | Shell command state used for merge |
afterShellExecution | ✓ | ✓ | One Shell span with command, cwd, output, and duration |
beforeMCPExecution | ✓ | MCP tool state used for merge | |
afterMCPExecution | ✓ | One MCP: {tool} span with input, result, and duration | |
beforeReadFile | ✓ | Read file span | |
afterFileEdit | ✓ | ✓ | File edit span |
beforeTabFileRead | ✓ | Tab read file span | |
afterTabFileEdit | ✓ | Tab file edit span | |
postToolUse | ✓ | ✓ | Generic tool span for non-shell, non-MCP tools |
stop | ✓ | ✓ | Stop span and state cleanup for the turn |
How Shell and MCP Merge Works
Cursor emits separatebefore* and after* hook events for shell commands and MCP tools. The Arize AX hooks keep a small disk-backed state entry for the before event, then create a single span on the corresponding after event. That gives you one span with both the input and the output instead of two partial spans.
On stop, the hook handler cleans up any saved state for that turn so the state directory does not keep growing over time.