Niches · Observability & incidents
Read and update incidents and on-call
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
The incident or schedule read with its body, alerts and timeline; any write (declare, note, override, coverage request) applied once even if retried, and the change visible on a re-read.
How agents ask for it: who is on call for payments
, open an incident for this
, add a timeline note
, find a cover for my shift next week
, get the alert body for this incident
Does the job, with a limit 6
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Better Stack C Better Stack, Inc. | Incident details, timeline and comments are separate read tools and on-call reads exist, but create incident takes no idempotency key and there is no override or coverage-request tool. source |
| Cronitor MCP server C Cronitor | Issues read with update history and are created, updated and resolved by tool; updates carry keys to avoid duplicate history, but create_issue has no stated dedup key and there is no on-call schedule. source |
| Grafana MCP Server BB Raintank Inc., d/b/a Grafana Labs | get_incident, add_activity_to_incident and OnCall schedule, shift and current-user reads exist, but no override or coverage write, and the README shows no idempotency key on create_incident. source |
| incident.io API B Pineapple Technology Ltd. | incident_show and incident_update_list give body and history; schedule_override_create and cover_request_create cover on-call; the REST API takes idempotency_key on incidents and escalations. MCP and API need Team or above, a blocker the map names. source |
| PagerDuty MCP Server E PagerDuty, Inc. | browse_incidents gets incidents, alerts and notes, manage_incidents adds notes and responders, manage_schedules creates overrides; but the body is missing without include[]=body (#65, open), no idempotency key is documented, and MCP needs Professional or above. source |
| Rootly MCP Server C Rootly Inc. | Incident and shift tools exist and create_override_shift writes overrides, but there is no coverage-request tool (#338, open, where the only write assigns someone without asking) and no idempotency key is documented. Essentials plan or above. source |
Doesn't do this job 6
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Axiom MCP Server BB Axiom, Inc. | Monitors and their alert history only; no incident, timeline, schedule or override tools. source |
| Causely MCP server E Causely, Inc. | No on-call schedules, and Issues are inferred diagnoses rather than incident records; the only write is snoozing an Issue. source |
| Datadog MCP Server D Datadog, Inc. | get_datadog_incident is documented as not including timeline data, no tool declares an incident or adds a note, and there are no on-call tools. source |
| Honeycomb MCP B Hound Technology, Inc. d/b/a Honeycomb | No incident, timeline or on-call tools. source |
| New Relic MCP Server B New Relic, Inc. | Alert events and issues are readable, but there are no incident writes, notes or on-call tools; the server is read-only. source |
| Sentry MCP B Functional Software, Inc. d/b/a Sentry | No incident records or on-call schedules; issues are errors, not incidents. source |
What stops agents finishing
- API or MCP gated to a paid tier (PagerDuty Professional, incident.io Team)
- write tool assigns a person without asking them
- duplicate incident or page after a retried create
Around it
Before: observability.investigate-alert, calendar.read-events. After: messaging.post-summary, notifications.page.
Where this comes from
Weight 12 of 100 in Observability & incidents: 6 of 42 accounts, four of them GitHub issues on PagerDuty and Rootly servers; incident.io named in two
The same as data: /api/v1/use-cases/observability.oncall-and-incident-records.json, or the MCP tool get_use_case with id observability.oncall-and-incident-records. Other jobs in this category: /api/v1/niches?category=observability.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.