Cursor
Cursor connector wires hooks.json with native ask on beforeShellExecution and beforeMCPExecution. Block on preToolUse, beforeReadFile, beforeTabFileRead, beforeSubmitPrompt, stop.
The Cursor connector wires DefenseClaw into Cursor's user-scoped hooks.json so every shell command and MCP tool call is inspected before it runs.
Setup
defenseclaw setup cursorCursor setup is supported on macOS and Linux. The DefenseClaw connector is not certified on native Windows x64, so setup rejects it there.
This runs the observe-mode template. Cursor talks directly to its native
upstream; DefenseClaw inspects via hooks. There is no proxy-enforcement
path for Cursor — blocking happens hook-side via preToolUse,
beforeShellExecution, beforeMCPExecution, beforeReadFile,
beforeTabFileRead, beforeSubmitPrompt, and stop. Native ask is supported
only on the two before*Execution events.
What setup cursor actually does
The table highlights convenience options rather than the complete alias
surface. The alias also accepts --mode, --rule-pack, --fail-mode,
approval, block-message, add/replace, workspace, and rule-pack-directory
options. See the quick-alias reference; use
full guardrail setup for scanner, detection-strategy,
and judge-provider configuration.
| Flag | Default | What it does |
|---|---|---|
--yes / -y | off | Skip the confirmation prompt. |
--restart / --no-restart | --restart | Bounce defenseclaw-gateway after applying changes so the new hooks wire in. |
--with-local-stack / --no-local-stack | --no-local-stack | Also run setup local-observability up; follow the command's printed gateway-restart step after it writes the export destination. |
setup cursor is the dedicated Cursor alias. It uses the shared guardrail
setup backend, defaults to observe mode, and can join an existing
hook-connector roster when you choose Add.
Common variations — pick the recipe that fits your phase
defenseclaw setup cursorConfirms once, wires the hooks against ~/.cursor/hooks.json, and restarts the gateway. Findings flow to mandatory SQLite event history and the TUI; configured v8 destinations receive only the buckets/signals their routes select. No traffic is intercepted and no requests are blocked. Pass --yes to skip the confirmation in CI.
defenseclaw setup cursor --yes --with-local-stackSame as standard but also runs setup local-observability up so Prom/Loki/Tempo/Grafana come up locally for ad-hoc dashboards. That command writes the export destination after the alias has already restarted the gateway, so run its printed defenseclaw-gateway restart step before expecting exports. See Local observability.
export DEFENSECLAW_LLM_KEY='replace-with-your-key'
defenseclaw setup cursor # base alias first
defenseclaw setup guardrail \
--connector cursor \
--rule-pack strict \
--scanner-mode local \
--detection-strategy regex_judge \
--judge-model anthropic/claude-sonnet-4-20250514 \
--judge-api-key-env DEFENSECLAW_LLM_KEY \
--judge-hook-connectors cursor \
--restartThe alias selects Cursor; the follow-up setup guardrail --connector cursor swaps in the strict rule pack, keeps scanning local, and turns the LLM judge on as a second-pass adjudicator on regex-flagged events. Configure the remote scanner separately through full guardrail setup, which validates its endpoint and API-key environment variable.
Cursor has no proxy enforcement, but its hooks can enforce directly:
defenseclaw setup cursor --mode action --human-approval --fail-mode closedWith mode=action, beforeShellExecution and beforeMCPExecution surface a
native ask when policy returns an eligible confirmation verdict. The other
block events use an alert/context fallback with raw_action preserved; the
TUI can review but not resume them.
Decision aids — should I turn this on?
Human-in-the-loop (HITL)
Per-connector ask matrix. Cursor supports native ask only on beforeShellExecution and beforeMCPExecution; other events use a non-pausing fallback.
Full setup guardrail flag reference
The complete flag surface for `setup guardrail --connector cursor`.
Defaults & rule packs
What permissive / default / strict actually ship, and which one matches your risk tolerance.
Interactive wizard
Animated terminal demo of the prompt-by-prompt setup flow — the safest path the first time.
Not sure what to pick? Run defenseclaw setup guardrail (no flags) — the interactive wizard walks you through every choice with safe defaults pre-selected and inline help. The Prompt → flag mapping table gives you the CI-shaped command for the same configuration.
Files DefenseClaw will modify
Cursor's MCP / skills / rules surfaces are discovered from user-global Cursor locations by default. Workspace-local overlays are included only when you explicitly pin a workspace.
Hook capabilities
Block events
- preToolUse
- beforeShellExecution
- beforeMCPExecution
- beforeReadFile
- beforeTabFileRead
- beforeSubmitPrompt
- stop
Native ask events
- beforeShellExecution
- beforeMCPExecution
Cursor supports native ask only on beforeShellExecution and
beforeMCPExecution. The other block events (preToolUse, beforeReadFile,
beforeTabFileRead, beforeSubmitPrompt, stop) return an alert/context
fallback and retain the original confirm intent in audit.
Disable
defenseclaw guardrail disable --connector cursor --yes