Cursor

Trace Cursor IDE and CLI conversations, shell commands, MCP tools, and file operations in Phoenix.

Trace Cursor IDE and CLI conversations, shell commands, MCP tools, and file operations in Phoenix for full observability.

Trace your Cursor sessions in Phoenix with the coding-harness-tracing toolkit — each conversation becomes a session and each message turn a trace, with the model’s response, shell commands, MCP tools, and file edits captured as nested spans. No application code changes required: the toolkit hooks into Cursor’s IDE and CLI events and streams OpenInference spans to Phoenix.

Launch Phoenix

The fastest way to get started with Phoenix is by signing up for a free Phoenix Cloud account. If you prefer, you can also run Phoenix in a notebook, self-host it, or use it directly from your terminal.

Go to the settings page in your Phoenix instance to find your endpoint and API key. A self-hosted Phoenix defaults to http://localhost:6006; the API key is only required when auth is enabled.

Install

The curl installer is the simplest — it runs a short wizard that saves your Phoenix credentials for you. Use a local clone if you’d rather run the installer from a checkout of the source.

Curl installer (recommended)

macOS / Linux:

curl -sSL https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.sh | bash -s -- cursor

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.bat -OutFile $env:TEMP\install.bat
& $env:TEMP\install.bat cursor

Local clone

git clone https://github.com/Arize-ai/coding-harness-tracing.git
cd coding-harness-tracing
./install.sh cursor        # macOS / Linux
install.bat cursor         # Windows

The installer prompts for your backend — select Phoenix, then enter your endpoint and optional API key — and your project name, writes them to ~/.arize/harness/config.json, 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.json. Environment variables override values in config.json and can be set in your shell profile so they apply to Cursor IDE and Cursor CLI sessions.

export PHOENIX_ENDPOINT="http://localhost:6006"
export PHOENIX_API_KEY="<your-api-key>"   # optional, only if auth is enabled
export PHOENIX_PROJECT="cursor"
export ARIZE_TRACE_ENABLED="true"

On the Phoenix backend, set the project name with PHOENIX_PROJECT (or PHOENIX_PROJECT_NAME); ARIZE_PROJECT_NAME is Arize-only and ignored here. ARIZE_TRACE_ENABLED is a backend-agnostic harness setting and keeps the ARIZE_ prefix regardless of destination.

Redaction controls

Each ARIZE_LOG_* flag accepts "true" or "false" and defaults to "true". Set to "false" to opt out per category:

export ARIZE_LOG_PROMPTS="false"
export ARIZE_LOG_TOOL_DETAILS="false"
export ARIZE_LOG_TOOL_CONTENT="false"

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 Phoenix. You’ll see:

• Session grouping by conversation_id for each Cursor conversation
• Turn traces by generation_id for 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

The default project name is cursor unless you set PHOENIX_PROJECT.

Cursor conversation grouped together in a single session view

Drill into any turn trace to inspect the full span tree, including the model response and nested shell, MCP, and file-operation spans.

Detailed trace view for a Cursor turn

How Shell and MCP Merge Works

Cursor emits separate before* and after* hook events for shell commands and MCP tools. The 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.

Reference

For the full list of environment variables, default file paths, and troubleshooting steps, see the Cursor tracing README.

Fail-Open Behavior

If the tracing hook errors, Cursor continues running. The hook handler always returns the permissive response Cursor expects, so tracing failures do not block the editor or agent workflow.

Uninstall

curl -sSL https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.sh | bash -s -- uninstall cursor

Resources

Arize Coding Harness Tracing

OpenInference

Cursor