Create a new endpoint in the current workspace. If environment_id is omitted, the workspace's default environment is used. environment_id accepts either an env_xxx id or a slug like "production"/"staging". Returns the created endpoint with its newly-generated public id. Example: user says "create a webhook for https://example.com/hook" → call with url="https://example.com/hook". If the user explicitly names an environment ("in staging"), pass it; otherwise omit and the default is used. For the full endpoint schema, see resource nahook://schemas/endpoint.

Fetch a single delivery by its public id (del_xxx). Returns status, attempt count, timestamps. Pass include_payload=true to also fetch the original webhook body — critical for debugging why a delivery failed. Adds one extra HTTP round-trip. Example: "why did del_xyz fail?" → call with delivery_id="del_xyz", include_payload=true to see the body the producer sent, then follow up with list_attempts to see what each HTTP attempt returned. For the full delivery schema and status value meanings, see resources nahook://schemas/delivery and nahook://schemas/delivery-statuses.

Fetch a single endpoint by its public id (ep_xxx). Example: user says "show me ep_abc" or "details of ep_abc". If the user references an endpoint without naming a specific ep_xxx id, call list_endpoints first to discover ids. For the full endpoint schema, see resource nahook://schemas/endpoint.

List every recorded attempt for a delivery, oldest first. Useful for debugging why a delivery failed. Example: "why did del_xyz fail?" → pair this with get_delivery (include_payload=true). get_delivery shows what the producer sent; list_attempts shows what each receiver attempt returned. Together they tell you whether the failure was producer-side (bad payload) or receiver-side (5xx, timeout).

List deliveries for an endpoint, newest-first. Paginate by passing next_cursor back as cursor on subsequent calls. Returns up to 200 per page (default 50). Example: "show me failed deliveries for ep_acme" → endpoint_id="ep_acme", status="failed". Requires an endpoint_id — if the user names a specific delivery (del_xxx) instead, use get_delivery. Valid status filters: pending, delivering, delivered, failed, scheduled_retry, dead_letter. For the full delivery schema and status value meanings, see resources nahook://schemas/delivery and nahook://schemas/delivery-statuses.

List every endpoint in the current workspace. Returns id, type, url, status (active/paused), is_active, created_at, and last_delivery_at for each. Example: user says "show me my webhooks" or "list my endpoints" → call with no args. This is the natural first call whenever the user names operations on an endpoint without giving a specific ep_xxx id — use the returned ids in follow-up calls. For the full endpoint schema, see resource nahook://schemas/endpoint.

List every environment in the current workspace. Use the returned id (env_xxx) or slug as environment_id when creating endpoints. Example: user says "what environments do I have". Most workspaces have a single default environment — only call this when the user mentions environments explicitly or you need to disambiguate where a new endpoint should land.

Re-enqueue a failed or dead-lettered delivery. The backend returns 409 if the delivery is in any other state. Returns the updated delivery row. Example: "retry del_xyz" → call with delivery_id="del_xyz". Only works when the delivery's status is failed or dead_letter — calling on delivered, pending, delivering, or scheduled_retry returns 409. Check status with get_delivery first if uncertain. For which statuses accept retry and which don't, see resource nahook://schemas/delivery-statuses.

Send a webhook directly to one endpoint (skips event-type fan-out). Pass idempotency_key for safe retries — duplicate keys return the original delivery id. Example: "send a test webhook to ep_abc with payload {...}" → endpoint_id="ep_abc", payload={...}. Use this when the user names a specific endpoint to target; use trigger_event when the user names an event type that should fan out to all subscribers.

Fire an event by event type — the backend fans it out to every endpoint subscribed to that type. Returns one delivery id per subscriber (empty if no subscribers). Use send_to_endpoint when you want to target one specific endpoint instead. Example: "fire an order.created event with order_id=ord_123" → event_type="order.created", payload={"order_id": "ord_123"}. An empty delivery_ids array means no endpoint subscribes to that event type — inspect subscriptions with list_endpoints if the user expected a non-empty result.

Patch an existing endpoint. Only fields explicitly set in the input are sent to the API; omit a field to leave it unchanged. Common uses: pause/resume via is_active, redirect via url. Example: "pause ep_abc" / "disable ep_abc" → endpoint_id="ep_abc", is_active=false. "resume ep_abc" / "enable ep_abc" → is_active=true. "point ep_abc at https://new.com" → endpoint_id="ep_abc", url="https://new.com". PATCH semantics matter: passing url="" would clear the URL, so don't include fields the user didn't ask to change. For the full endpoint schema, see resource nahook://schemas/endpoint.

Return the workspace, region, and token id the local Nahook CLI is logged into. Use this as a first call to confirm credentials are in place. Reads ~/.nahook/config.toml; never hits the network. Example: "am I logged in?", "what workspace am I in?". Also worth calling defensively before other tools if you suspect credentials might be missing — it tells you whether nahook login has run.