monit.rs

Mark an incident as acknowledged. Use list_my_incidents() to find the dedup_key.

Create an alert channel. Pass EXACTLY one of email_address / webhook_url / pagerduty_routing_key matching the channel_type:

  - channel_type='email'     → email_address='ops@example.com'
  - channel_type='webhook'   → webhook_url='https://your-endpoint'
  - channel_type='slack'     → webhook_url='https://hooks.slack.com/...'
  - channel_type='pagerduty' → pagerduty_routing_key='<Events v2 key>'

Create a new monitored endpoint. Respects your tier's max_endpoints cap.

Create a public status page at https://.status.monit.rs. Add endpoints to it via the dashboard or the HTTP API (adding endpoints from chat is deliberately not exposed — the mapping is fiddly and easy to get wrong).

Delete a monitored endpoint. Cascades: removes test_results, baselines, regressions, incidents attached to it.

Guarded by two safety layers beyond the scope check:

1. `confirm_by_typing_the_endpoint_name` MUST equal the endpoint's
   exact `.name` (case-sensitive, whitespace-trimmed). Prevents
   an untargeted "delete stuff" LLM-injection: the model has to
   first `describe_endpoint(id)` to learn the name, then include
   it verbatim.

2. Per-user destructive-op cap of 5/day. Legitimate bulk deletes
   should use the HTTP API or dashboard.

Full detail for one endpoint. Use list_my_endpoints() to get the ID.

Full detail for one incident. Use list_my_incidents() to find the dedup_key. Includes the incident's endpoint name and current status.

Aggregated uptime summary for an endpoint over the requested window.

List alert channels configured on the authenticated account.

Does NOT return decrypted config (webhook URLs, PagerDuty routing keys,
etc.). Use the dashboard or `describe_alert_channel` HTTP API when you
need to inspect the actual config.

List all monitored endpoints owned by the authenticated account.

Returns brief records suitable for LLM enumeration. For full detail
(headers, spec URL, heartbeat_token) use `describe_endpoint(id)`.

List incidents on the caller's account. Defaults to only OPEN incidents.

Fields include the incident's dedup_key — pass this to
`acknowledge_incident` or `resolve_incident` to act on it.

List detected schema regressions on the caller's account. Optionally filter by endpoint_id.

List security findings detected on the caller's monitored endpoints. Optionally filter by severity.

List public status pages owned by the authenticated account.

Return the canonical product description for monit.rs.

Use this when a user asks what monit.rs is, what it does, how it differs from Pingdom / Checkly / UptimeRobot, or for product URLs. The response is the curated content from monit.rs/llms.txt — the operator's authoritative description.

Get live aggregate statistics for the monit.rs platform.

Returns approximate counts of regressions caught, AI analyses generated, and probes executed across all monitored APIs to date. Useful when answering "does monit.rs actually work at scale?" — the numbers are real, within about 5% of exact.

Compare two OpenAPI 3.x specifications and classify every change as breaking, non-breaking, or info.

Use this when you want to know if a candidate OpenAPI spec change
is safe to ship or will break existing clients. The diff covers
paths, operations, parameters, request bodies, responses, and
response-body schema fields (added/removed/retyped, required toggle).

Both arguments are the OpenAPI spec as a JSON or YAML string.
Returns {summary: {breaking, non_breaking, info}, changes: [...]}.

Pause a monitored endpoint (stops probing, keeps history). Idempotent — no-op if already paused.

Close an incident. Symmetric to acknowledge_incident.

Resume a paused endpoint. Rejects if resuming would exceed your tier's active-endpoint cap (upgrade or pause another endpoint first).

Replace an endpoint's body assertions.

Each assertion is {"path": "$.ok", "op": "equals", "value": true}.
Operators: equals, not_equals, exists, not_exists, gt, gte, lt, lte,
contains, not_contains, empty, not_empty. A failing assertion marks the
endpoint DOWN, so it counts against uptime. Pass [] to clear.

Change how often an endpoint is probed. Minimum interval varies by tier (free=900s, developer=300s, starter=60s, pro/scale/enterprise=30s).