Skip to content
Agentmart
Submit a tool

Rootly

Incident management, on-call scheduling, and intelligent analysis powered by Rootly.

Connector by rootly.comOfficial · Domain verified by the MCP Registry

IndexedApache-2.0Local (stdio)Remote (SSE)★ 45
Write a review

Install

Works with Claude Code, VS Code, Codex, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/rootly-com-mcp-server

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://mcp.rootly.com/sse Remote (SSE)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Incident management, on-call scheduling, and intelligent analysis powered by Rootly.

Use cases: incident-response, scheduling

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
21 read · 3 write · 0 delete · 1 not yet classified
Secrets
2 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Python package

Tools by what they do 25

Read from the source code; the running server may list different tools.

Read 21 · Look things up without changing anything.

  • check_oncall_health_risk
  • check_responder_availability
  • find_related_incidents
  • get_alert_by_short_id
  • get_incident
  • get_incident_meeting_transcripts
  • get_incident_retrospective
  • get_oncall_handoff_summary
  • get_oncall_schedule_summary
  • get_oncall_shift_metrics
  • get_schedule_shifts
  • get_server_version
Show 9 more tools
  • get_shift_incidents
  • list_audits
  • list_endpoints
  • list_incident_post_mortems
  • list_incident_roles
  • list_incidents
  • list_shifts
  • search_incidents
  • suggest_solutions

Write 3 · Create, change, send or run things.

  • create_incident
  • create_override_recommendation
  • update_incident

Not yet classified 1 · We could not tell from the name and description.

  • collect_incidents

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • Authorization
  • ROOTLY_API_TOKEN

Network hosts it talks to 1

  • mcp.rootly.com · found in remote endpoint, install command

Files it touches

  • Any path the agent passes to its tools

Tools (25)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_oncall_health_risk

    Check if any at-risk responders (based on On-Call Health analysis) are scheduled for on-call. Integrates with On-Call Health (oncallhealth.ai) to identify responders with elevated workload health risk and checks if they are scheduled during the specified period. Optionally recommends safe replacement responders. Privacy: This tool surfaces identifiable employee workload health data from On-Call Health. It is an opt-in feature — an administrator must explicitly configure the ONCALLHEALTH_API_KEY environment variable to enable it. Available only in self-hosted deployments. Requires ONCALLHEAL…

  • check_responder_availability

    Check if specific users are scheduled for on-call in a date range. Use this to verify if at-risk users (from On-Call Health) are scheduled, or to check availability before assigning new shifts. Returns scheduled users with their shifts and total hours, plus users who are not scheduled. Shift times and hours are clipped to the requested window; date-only end dates include that entire UTC day.

  • collect_incidents

    Collect a bounded working set of incidents across multiple pages for audits and analysis. Use this instead of list_incidents when you want a compact batch of incidents in one tool call, while keeping payload size under control. Argument caps: max_results <= 100, batch_size between 10 and 100. Values outside those bounds are clamped and reported, not rejected.

  • create_incident

    Create an incident with a scoped set of fields for agent-driven workflows.

  • create_override_recommendation

    Recommend replacement responders for an override shift. Finds users in the same schedule rotation who are not already heavily loaded during the period. Returns recommended replacements sorted by current load (lowest first), plus a ready-to-use override payload for the top recommendation.

  • find_related_incidents

    🔍 Find historically similar incidents using ML similarity analysis - CRITICAL for incident response. WHEN TO USE: • EARLY in incident response to learn from past similar issues • When you're unsure about root cause or resolution approach • Before escalating to find if this is a known pattern • For post-incident analysis to identify recurring issues Provide either incident_id OR incident_description (e.g., 'website is down', 'database timeout errors'). Use status_filter to limit to specific incident statuses or leave empty for all incidents. Argument caps: max_results <= 20. Values outside …

  • get_alert_by_short_id

    Get alert details by short_id or alert URL. Use this when a user pastes an alert URL or short_id from a pager notification and wants to investigate the alert.

  • get_incident

    Retrieve a single incident with PIR-related fields for direct verification.

  • get_incident_meeting_transcripts

    Read what was said on an incident's calls (Rootly Meeting Scribe). Returns the spoken transcript of each recorded call for the incident, as text per speaker turn, alongside Scribe's own summary. Covers Google Meet, Zoom and Microsoft Teams calls that Scribe recorded. Use this to catch up on a call you missed, or to pull decisions and actions out of an incident bridge. Recordings where nobody spoke are skipped rather than returned empty.

  • get_incident_retrospective

    Fetch the written retrospective for one incident. Answers "what did we learn from INC-4460" in a single call. Returns the document's title, content and status alongside the incident it belongs to, and reports the incident's retrospective progress so a blank document is distinguishable from one nobody has started. The route exists only in this direction: `/post_mortems` cannot be filtered by incident, and the document carries no reference back to one, so the id has to come from the incident's own relationship. Doing that here keeps a caller from having to know it. Use `list_incident_post_mort…

  • get_oncall_handoff_summary

    Get current on-call handoff summary. Shows who's currently on-call and who's next. Optionally fetch incidents (set include_incidents=True, but slower). Each responder's `role` is their On-Call role (e.g. Responder, Admin); shifts themselves carry no role. Use filter_by_region=True with a timezone to see only people on-call during business hours in that region (e.g., timezone='Asia/Tokyo', filter_by_region=True shows only APAC on-call during APAC business hours). Useful for: - Quick on-call status checks - Daily handoff meetings - Regional on-call status (APAC, EU, Americas) - Team coordinati…

  • get_oncall_schedule_summary

    Get compact on-call schedule summary for a date range. Returns one entry per user per schedule (not raw shifts), with aggregated hours. Optimized for AI agent context windows. Use this instead of list_shifts when you need: - Aggregated hours per responder - Schedule coverage overview - Responder load analysis with warnings One row per user per schedule, so the response stays the same size whether the range is a week or a year. For individual shift times, or for one person's schedule, use list_shifts instead. Ranges longer than the upstream cap are split into windows and merged automaticall…

  • get_oncall_shift_metrics

    📊 Get on-call workload metrics and shift statistics - ESSENTIAL for fairness and planning. WHEN TO USE: • Monthly/quarterly reviews of on-call distribution • Before adjusting schedules to ensure fair workload • For management reporting on on-call burden • When investigating potential on-call burnout Returns shift counts, total hours, and statistics grouped by user, schedule, or team. Examples: - Monthly report: start_date='2025-10-01', end_date='2025-10-31' - Specific user: start_date='2025-10-01', end_date='2025-10-31', user_ids='123,456' - Specific team: team_ids='team-1' (will query sch…

  • get_schedule_shifts

    List shifts for one schedule over a date range. Replaces the generated getScheduleShifts, which passed the range straight through and failed with `Datetime range exceeds 1 month` on anything longer than the upstream accepts. Ranges longer than that are split into windows and merged here, so a two-month question is a normal request. Use list_shifts instead when the question spans schedules or filters by user.

  • get_server_version

    Get the Rootly MCP server version. Returns the current version of the deployed MCP server. Useful for checking if the server has been updated.

Show 10 more tools
  • get_shift_incidents

    Get incidents and alerts that occurred during a specific shift or time period. Useful for: - Shift handoff summaries showing what happened during the shift - Post-shift debriefs and reporting - Incident analysis by time period - Understanding team workload during specific shifts Returns incident details including severity, status, duration, and basic summary.

  • list_audits

    Read the Rootly audit log: who changed which configuration object, when, and what changed. Each record carries the action, the acting user, the source, and the before-and-after value of every modified field. Use it to answer "who changed this escalation policy", "what did this workflow look like before", or to collect change evidence for a compliance review. Covers roughly 60 resource types at the object level and is retained indefinitely. Two limits worth knowing: schedule rotations, escalation levels and shift overrides are not audited, and sign-in events are kept separately from this log.…

  • list_endpoints

    List all available Rootly API endpoints with their descriptions.

  • list_incident_post_mortems

    Browse retrospectives across incidents. Answers "the last five retrospectives", "published ones for this team since June", or "how many are still draft". Each result carries the document's analysis -- summary, causes, impact, actions. A recognised Timeline is dropped and the record says so with `timeline_omitted`, because a minute-by-minute log is a third of a document and rarely what a browse is after. What remains is still capped, and a record cut that way carries `content_truncated` with its real `content_chars`. Use `get_incident_retrospective` for one document whole, Timeline included an…

  • list_incident_roles

    List role assignments for an incident (who is Commander, Scribe, etc.). Returns one entry per defined role with role metadata and the assigned user (or `user_id: null` for roles that are defined on the incident but not yet assigned). Use this to answer questions like "who is the incident commander?", "is there a postmortem owner?", or "list all roles for INC-4460". Implementation note: this wraps `GET /v1/incidents/{id}?include=roles` and flattens the JSON:API `included` array of `incident_role_assignments` into a flat table so callers don't need to walk the relationships graph.

  • list_incidents

    🚨 List incidents with structured filters - ESSENTIAL for incident response. WHEN TO USE: • During incident response to check for related ongoing incidents • For shift handoffs to review recent incidents by team/service • For post-incident analysis to find patterns by severity/date range • For audit workflows requiring specific filtering criteria Use this when you need date-range, team, service, severity, or status filters. For simple text searches, prefer search_incidents instead. Argument caps: page_size <= 100. Values outside the bounds are clamped and reported, not rejected.

  • list_shifts

    List on-call shifts with reliable filtering, enrichment, and MCP-level pagination. Unlike the raw API, this tool: - Actually filters by user_ids (client-side filtering) - Includes user_name, user_email, schedule_name, team_name - Calculates total_hours for each shift - Returns a predictable paginated result for MCP clients Use this instead of the auto-generated listShifts when you need user filtering or dependable pagination on large tenants. Answers questions about *individual* shifts: who is on call at a given time, when a handoff happens, which shifts were overrides, or one person's sche…

  • search_incidents

    Search incidents with flexible pagination control. Use page_number=0 to fetch all matching results across multiple pages. Use page_number>0 to fetch a specific page. max_results (also accepted as `limit`) caps how many incidents come back in either mode: across pages when page_number=0, and within the page otherwise. Left unset, a single page returns page_size incidents and page_number=0 stops at 5. Argument caps: page_size <= 20, max_results <= 10. Values outside those bounds are clamped and reported, not rejected.

  • suggest_solutions

    💡 Get actionable solution recommendations from similar resolved incidents - KEY for incident response. WHEN TO USE: • AFTER find_related_incidents to get specific resolution steps • When team is stuck on how to resolve the current incident • To speed up incident resolution with proven solutions • For training new responders on resolution patterns Provide either incident_id OR title/description. Defaults to resolved incidents for solution mining. Argument caps: max_solutions <= 10. Values outside the bounds are clamped and reported, not rejected.

  • update_incident

    Update native incident fields via ``PUT /v1/incidents/{id}``. Only the arguments you provide are sent, so unspecified fields — including the lifecycle ``status`` — are left untouched.

Compare and alternatives

Signals

Stars
45
Forks
24
Open issues
0
Contributors
16
Weekly downloads
1,174
Last commit
Oct 24, 2026 (4 days ago)
Last release
Feb 18, 2026 (8 months ago)
Last package publish
Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
com.rootly/mcp-server
Version
2.2.4
Auth
Bearer token, API key
Packages
pypi rootly-mcp-server
License
Apache-2.0
Repository
github.com/Rootly-AI-Labs/Rootly-MCP-server
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Rootly MCP server. Agent Mart. https://agentmart.dev/connectors/rootly-com-mcp-server (last updated 2026-10-24)