Rootly MCP server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ROOTLY_API_TOKEN | No | Your Rootly API token | |
| ROOTLY_AUTH_HEADER | No | Bearer token for authentication (format: Bearer <YOUR_ROOTLY_API_TOKEN>) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_endpointsA | List all available Rootly API endpoints with their descriptions. |
| get_server_versionA | Get the Rootly MCP server version. Returns the current version of the deployed MCP server. Useful for checking if the server has been updated. |
| list_incidentsA | 🚨 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. |
| collect_incidentsA | 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. |
| search_incidentsA | 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 Argument caps: page_size <= 20, max_results <= 10. Values outside those bounds are clamped and reported, not rejected. |
| get_incidentA | Retrieve a single incident with PIR-related fields for direct verification. |
| get_incident_retrospectiveA | 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: |
| list_incident_post_mortemsA | 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 Filtering happens upstream for status, severity, team, service and
dates. Free-text search is not offered here because the API's search
matches titles only, and titles are generated from the incident name --
it cannot find a retrospective by what it says. Use
|
| list_incident_rolesA | List role assignments for an incident (who is Commander, Scribe, etc.). Without Returns one entry per defined role with role metadata and the assigned
user (or Implementation note: this wraps |
| get_incident_meeting_transcriptsA | 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. |
| create_incidentC | Create an incident with a scoped set of fields for agent-driven workflows. |
| update_incidentA | Update native incident fields via Only the arguments you provide are sent, so unspecified fields —
including the lifecycle |
| find_related_incidentsA | 🔍 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 the bounds are clamped and reported, not rejected. |
| suggest_solutionsA | 💡 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. |
| get_oncall_shift_metricsA | 📊 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:
|
| get_oncall_handoff_summaryA | 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 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:
|
| get_shift_incidentsB | Get incidents and alerts that occurred during a specific shift or time period. Useful for:
Returns incident details including severity, status, duration, and basic summary. |
| get_schedule_shiftsA | List shifts for one schedule over a date range. Replaces the generated getScheduleShifts, which passed the range
straight through and failed with Use list_shifts instead when the question spans schedules or filters by user. |
| list_shiftsA | List on-call shifts with reliable filtering, enrichment, and MCP-level pagination. Unlike the raw API, this tool:
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 schedule (via user_ids). For questions about totals across a team -- hours per responder, coverage, load -- use get_oncall_schedule_summary, whose response size depends on team size rather than on how long a range you asked for. Ranges longer than the upstream cap are split into windows and merged automatically, so a multi-month range is a normal request. |
| get_oncall_schedule_summaryA | 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:
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 automatically. |
| check_responder_availabilityA | 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. |
| create_override_recommendationA | 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. |
| check_oncall_health_riskA | 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 ONCALLHEALTH_API_KEY environment variable. |
| get_alert_by_short_idA | 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. |
| list_auditsA | 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. Returns a single page of at most 25 records, newest first, alongside
Requires an API token whose role has the "Audits - read" permission. |
| get_workflow_task_params_schemaA | Get the task_params fields for one workflow task type. Call this before create_workflow_task or update_workflow_task: their task_params schema lists only the task types, not each type's fields. Pass the result's fields inside data.attributes.task_params, together with task_type. |
| list_investigationsB | List AI SRE investigations you can see, newest first. |
| get_investigationA | Get an investigation's verdict: summary, root cause, confidence, hypotheses, evidence, causal chain and open_questions (what Rootly couldn't verify, so you can check them with tools only you have). |
| get_investigation_progressA | Follow a running investigation. Returns new steps and tool calls since after_cursor, waiting up to wait_seconds for them. Keep calling with after_cursor=next_cursor until done is true. |
| start_investigationA | Start an AI SRE investigation on one alert or incident. Then follow it with get_investigation_progress. |
| cancel_investigationB | Cancel a running investigation. |
| list_ai_automation_runsA | List recent runs of one AI automation with status, trigger and timing. Read-only. Scans the 1000 most recent runs matching the filters; pagination and counts cover the visible runs in that window. When meta.next_scan_cursor is set, older runs exist beyond the window. Present only on the last page of the current scan window; finish page pagination before following it. Repeat the request with filter[scan_cursor] set to that opaque cursor to continue. Incident-linked runs are visible only when the caller's role permits access. OAuth tokens also need the |
| run_ai_automationA | Run an existing AI automation now, once. The run executes that automation's saved prompt with only the tools in its Requires OAuth scope |
| get_ai_automation_runA | Get one AI automation run by id: its status, timing, what triggered it, the linked incident if any, and the agent's output. Read-only. Incident-linked runs are visible only when the caller's role permits access. OAuth tokens also need the |
| list_ai_automation_slack_channelsB | Channels Rootly has synced from the team's connected Slack workspace; any returned slack_channel_id is accepted as destination_slack_channel_id. When filter[search] is set, exact channel-name matches come first. When Slack channel user filtering is enabled, personal keys and OAuth tokens only see, and can only set new, channels the user can access in Slack; an update may resend the automation's current channel unchanged. |
| list_ai_automation_slack_usersB | Users, including bots, from the team's connected Slack workspace; any returned slack_user_id is accepted by user and item_user trigger conditions. |
| list_ai_automation_slack_user_groupsB | User groups from the team's connected Slack workspace, read live from Slack; any returned slack_user_group_id is accepted by usergroup trigger conditions. |
| get_ai_automation_trigger_optionsC | Returns the source-of-truth options used by the AI Automation editor. |
| list_ai_automationsA | List the team's AI automations: name, prompt, triggers, destination, allowed tools, run limits and whether each is enabled. Read-only. An AI automation is a saved instruction (prompt) that a Rootly AI agent runs on a schedule, on a matching event (incident, alert, Slack message, webhook) or on demand. When it runs, the agent may only use the tools listed in the automation's Requires OAuth scope |
| create_ai_automationA | Create an AI automation. Set Requires OAuth scope |
| get_ai_automationA | Get one AI automation by id: its prompt, triggers, destination, allowed tools, attached skills and run limits. Read-only. An AI automation is a saved instruction (prompt) that a Rootly AI agent runs on a schedule, on a matching event (incident, alert, Slack message, webhook) or on demand. When it runs, the agent may only use the tools listed in the automation's Requires OAuth scope |
| update_ai_automationA | Change an existing AI automation. Only the attributes you send change; Requires OAuth scope |
| list_ai_skill_versionsA | List the saved versions of one AI skill, newest first. Read-only. An AI skill is reusable written guidance (markdown Requires OAuth scope |
| get_ai_skill_versionA | Get one saved version of an AI skill, including the Requires OAuth scope |
| list_ai_skillsA | List the team's AI skills: name, slug, description, who may invoke each and whether it is enabled. Read-only. An AI skill is reusable written guidance (markdown Requires OAuth scope |
| create_ai_skillA | Create an AI skill from a Requires OAuth scope |
| get_ai_skillA | Get one AI skill by id, including its current Requires OAuth scope |
| update_ai_skillA | Change an AI skill. Only the attributes you send change, and the change applies to every agent and automation that loads the skill. An AI skill is reusable written guidance (markdown Requires OAuth scope |
| list_alert_eventsC | List alert_events |
| create_alert_eventC | Creates a new alert event |
| get_alert_eventA | Retrieves a specific alert_event by id |
| update_alert_eventA | Updates a specific alert event. Only alert events with kind 'note' (user-created notes) can be updated. System-generated events are immutable to maintain audit trail integrity. |
| list_alert_groupsD | List alert groups |
| create_alert_groupC | Creates a new alert group. Note: For enhanced functionality and future compatibility, consider using the advanced alert grouping with |
| get_alert_groupB | Retrieves a specific alert group by id |
| update_alert_groupB | Update a specific alert group by id. Note: For enhanced functionality and future compatibility, consider using the advanced alert grouping with |
| list_alert_routesB | List all alert routes for the current team with filtering and pagination. Note: This endpoint requires access to Advanced Alert Routing. If you're unsure whether you have access to this feature, please contact Rootly customer support. |
| create_alert_routeA | Creates a new alert route from provided data. Note: This endpoint requires access to Advanced Alert Routing. If you're unsure whether you have access to this feature, please contact Rootly customer support. Asynchronous Rule CreationFor organizations with large numbers of routing rules, Rootly supports asynchronous rule processing to improve performance. When enabled, rule creation happens in the background. Asynchronous processing is also applied automatically, whether or not it is enabled for your organization, when a request carries a rule graph too large to save within the request timeout. Size is measured in total dependent records — rules plus their condition groups, conditions and destinations — and for an update it includes the rules already on the route, not just those in the payload. Important: Whenever rules are processed asynchronously, the rules list in the API response will not be up-to-date immediately after creation. You should refetch the alert route, or poll the async rule creation status endpoint with the If you experience slow operations when managing alert routes with many rules, contact Rootly customer support to enable asynchronous rule processing for your organization. |
| get_alert_routeA | Get a specific alert route by id. Note: This endpoint requires access to Advanced Alert Routing. If you're unsure whether you have access to this feature, please contact Rootly customer support. Optional Parameters
Example: |
| update_alert_routeA | Update a specific alert route by id. Note: This endpoint requires access to Advanced Alert Routing. If you're unsure whether you have access to this feature, please contact Rootly customer support. Asynchronous Rule CreationFor organizations with large numbers of routing rules, Rootly supports asynchronous rule processing to improve performance. When enabled, rule updates happen in the background. Asynchronous processing is also applied automatically, whether or not it is enabled for your organization, when a request carries a rule graph too large to save within the request timeout. Size is measured in total dependent records — rules plus their condition groups, conditions and destinations — and includes the rules already on the route, not just those in the payload, so a small payload against a large route may still be processed asynchronously. Important: Whenever rules are processed asynchronously, the rules list in the API response will not be up-to-date immediately after update. You should refetch the alert route, or poll the async rule creation status endpoint with the If you experience slow operations when managing alert routes with many rules, contact Rootly customer support to enable asynchronous rule processing for your organization. |
| patch_alert_routeB | Updates an alert route. Note: This endpoint requires access to Advanced Alert Routing. If you're unsure whether you have access to this feature, please contact Rootly customer support. |
| list_alert_routing_rulesB | List alert routing rules. Note: If you are an advanced alert routing user, you should use the Alert Routes endpoint instead of this endpoint. If you don't know whether you are an advanced user, please contact Rootly customer support. |
| create_alert_routing_ruleA | Creates a new alert routing rule from provided data. Note: If you are an advanced alert routing user, you should use the Alert Routes endpoint instead of this endpoint. If you don't know whether you are an advanced user, please contact Rootly customer support. |
| get_alert_routing_ruleA | Retrieves a specific alert routing rule by id. Note: If you are an advanced alert routing user, you should use the Alert Routes endpoint instead of this endpoint. If you don't know whether you are an advanced user, please contact Rootly customer support. |
| update_alert_routing_ruleC | Update a specific alert routing rule by id. Note: If you are an advanced alert routing user, you should use the Alert Routes endpoint instead of this endpoint. If you don't know whether you are an advanced user, please contact Rootly customer support. |
| list_alert_urgenciesD | List alert urgencies |
| create_alert_urgencyD | Creates a new alert urgency from provided data |
| get_alert_urgencyB | Retrieves a specific alert urgency by id |
| update_alert_urgencyC | Update a specific alert urgency by id |
| list_alerts_sourcesD | List alert sources |
| create_alerts_sourceC | Creates a new alert source from provided data |
| get_alerts_sourceC | Retrieves a specific alert source by id |
| update_alerts_sourceC | Update a specific alert source by id |
| list_incident_alertsC | List incident alerts |
| attach_alertC | Attach alerts to an incident from provided data |
| list_alertsD | List alerts |
| create_alertC | Creates a new alert from provided data |
| get_alertC | Retrieves a specific alert by id |
| update_alertD | Updates an alert |
| acknowledge_alertC | Acknowledges a specific alert by id |
| resolve_alertC | Resolves a specific alert by id |
| list_catalog_entitiesD | List Catalog Entities |
| create_catalog_entityD | Creates a new Catalog Entity from provided data |
| get_catalog_entityB | Retrieves a specific Catalog Entity by id |
| update_catalog_entityC | Update a specific Catalog Entity by id |
| list_catalog_propertiesC | List Catalog Properties - returns catalog_properties type |
| create_catalog_propertyC | Creates a new Catalog Property - returns catalog_properties type |
| get_catalog_propertyB | Retrieves a specific Catalog Property by id - returns catalog_properties type |
| update_catalog_propertyC | Update a specific catalog_property by id - returns catalog_properties type |
| list_catalogsD | List catalogs |
| create_catalogC | Creates a new catalog from provided data |
| get_catalogC | Retrieves a specific catalog by id |
| update_catalogC | Update a specific catalog by id |
| list_causesD | List causes |
| create_causeC | Creates a new cause from provided data |
| get_causeC | Retrieves a specific cause by id |
| update_causeC | Update a specific cause by id |
| list_custom_formsD | List custom forms |
| create_custom_formC | Creates a new custom form from provided data |
| get_custom_formB | Retrieves a specific custom form by id |
| update_custom_formC | Update a specific custom form by id |
| list_dashboard_panelsB | List dashboard panels. OAuth tokens need the |
| create_dashboard_panelA | Creates a new dashboard panel from provided data. OAuth tokens need the |
| get_dashboard_panelA | Retrieves a specific dashboard panel by id. OAuth tokens need the |
| update_dashboard_panelB | Update a specific dashboard panel by id. OAuth tokens need the |
| list_dashboardsB | List dashboards. OAuth tokens need the |
| create_dashboardB | Creates a new dashboard from provided data. OAuth tokens need the |
| get_dashboardA | Retrieves a specific dashboard by id. OAuth tokens need the |
| update_dashboardB | Update a specific dashboard by id. OAuth tokens need the |
| list_environmentsD | List environments |
| create_environmentC | Creates a new environment from provided data |
| get_environmentC | Retrieves a specific environment by id |
| update_environmentC | Update a specific environment by id |
| list_escalation_policiesD | List escalation policies |
| create_escalation_policyC | Creates a new escalation policy from provided data |
| get_escalation_policyB | Retrieves a specific escalation policy by id |
| update_escalation_policyC | Update a specific escalation policy by id |
| list_escalation_levelsC | List escalation levels |
| create_escalation_levelC | Creates a new escalation level from provided data |
| list_escalation_levels_pathsC | List escalation levels |
| create_escalation_level_pathsC | Creates a new escalation level from provided data |
| get_escalation_levelC | Retrieves a specific escalation level by id |
| update_escalation_levelC | Update a specific escalation level by id |
| list_escalation_pathsC | List escalation paths |
| create_escalation_pathC | Creates a new escalation path from provided data |
| get_escalation_pathC | Retrieves a specific escalation path by id |
| update_escalation_pathB | Update a specific escalation path by id |
| list_form_field_optionsD | List form_field_options |
| create_form_field_optionC | Creates a new form_field_option from provided data |
| get_form_field_optionA | Retrieves a specific form_field_option by id |
| update_form_field_optionC | Update a specific form_field_option by id |
| get_form_field_placement_conditionB | Retrieves a specific form_field_placement_condition by id |
| update_form_field_placement_conditionC | Update a specific form_field_placement_condition by id |
| get_form_field_placementC | Retrieves a specific form_field_placement by id |
| update_form_field_placementC | Update a specific form_field_placement by id |
| list_form_fieldsD | List form_fields |
| create_form_fieldC | Creates a new form_field from provided data |
| get_form_fieldC | Retrieves a specific form_field by id |
| update_form_fieldC | Update a specific form_field by id |
| get_form_set_conditionC | Retrieves a specific form_set_condition by id |
| update_form_set_conditionC | Update a specific form_set_condition by id |
| list_form_setsB | List form_sets. Without |
| create_form_setC | Creates a new form_set from provided data |
| get_form_setC | Retrieves a specific form_set by id |
| update_form_setC | Update a specific form_set by id |
| list_functionalitiesD | List functionalities |
| create_functionalityC | Creates a new functionality from provided data |
| get_functionalityC | Retrieves a specific functionality by id |
| update_functionalityC | Update a specific functionality by id |
| get_functionality_incidents_chartC | Get functionality incidents chart |
| get_functionality_uptime_chartC | Get functionality uptime chart |
| list_workflow_tasksD | List workflow tasks |
| create_workflow_taskA | Add a task to a Rootly workflow. Set Creates a new workflow task from provided data |
| get_workflow_taskB | Retrieves a specific workflow_task by id |
| update_workflow_taskA | Change a task in a Rootly workflow: its name, position, enabled state or Update a specific workflow task by id |
| list_workflow_form_field_conditionsC | List workflow form field conditions |
| create_workflow_form_field_conditionC | Creates a new workflow form field condition from provided data |
| get_workflow_form_field_conditionC | Retrieves a specific workflow form field condition by id |
| update_workflow_form_field_conditionC | Update a specific workflow form field condition by id |
| list_workflow_groupsD | List workflow groups |
| create_workflow_groupC | Creates a new workflow group from provided data |
| get_workflow_groupC | Retrieves a specific workflow group by id |
| update_workflow_groupC | Update a specific workflow group by id |
| list_workflow_runsC | List workflow runs |
| create_workflow_runA | Run a Rootly workflow now. The workflow executes its configured tasks (for example posting Slack messages, creating tickets, or changing the incident), which can act on other systems and cannot be undone by this server. Pass the record to run it against (such as Creates a new workflow run from provided data |
| list_workflowsD | List workflows |
| create_workflowC | Creates a new workflow from provided data |
| get_workflowC | Retrieves a specific workflow by id |
| update_workflowC | Update a specific workflow by id |
| list_heartbeatsD | List heartbeats |
| create_heartbeatC | Creates a new heartbeat from provided data |
| get_heartbeatB | Retrieves a specific heartbeat by id |
| update_heartbeatC | Update a specific heartbeat by id |
| list_incident_action_itemsC | List incident action items |
| create_incident_action_itemB | Add a follow-up action item to an incident: a Creates a new action item from provided data |
| get_incident_action_itemsC | Retrieves a specific incident_action_item by id |
| update_incident_action_itemC | Update a specific incident action item by id |
| list_all_incident_action_itemsC | List all action items for an organization |
| list_incident_eventsC | List incident events |
| create_incident_eventC | Creates a new event from provided data |
| list_incident_form_field_selectionsC | List incident form field selections |
| create_incident_form_field_selectionC | Creates a new incident form field selection from provided data |
| get_incident_form_field_selectionC | Retrieves a specific incident form field selection by id |
| update_incident_form_field_selectionC | Update a specific incident form field selection by id |
| get_incident_retrospective_stepB | Retrieves a specific incident retrospective step by id |
| update_incident_retrospective_stepC | Update a specific incident retrospective step by id |
| get_incident_sub_statusC | Retrieves a specific incident_sub_status by id |
| update_incident_sub_statusA | Correct one entry in an incident's sub-status history: which sub-status it records ( Update a specific incident_sub_status by id |
| list_incident_typesD | List incident types |
| create_incident_typeC | Creates a new incident_type from provided data |
| get_incident_typeB | Retrieves a specific incident_type by id |
| update_incident_typeC | Update a specific incident_type by id |
| list_live_call_routersD | List Live Call Routers |
| create_live_call_routerC | Creates a new Live Call Router from provided data |
| get_live_call_routerB | Retrieves a specific Live Call Router by id |
| update_live_call_routerC | Update a specific Live Call Router by id |
| list_meeting_recordingsA | List all meeting recording sessions for an incident. Returns recordings sorted by session number. Each recording represents one bot session with its own transcript, status, and metadata. |
| list_all_meeting_recordingsA | List meeting recordings across the organization. Returns the current user's standalone recordings plus incident-backed recordings the user can access. Supports filtering by status, platform, and created_by. |
| get_meeting_recordingB | Retrieve a single meeting recording session including its status, duration, speaker count, word count, and transcript summary. |
| list_observability_logsA | Search Rootly Observability logs with the Logs explorer query syntax ( |
| list_observability_patternsA | List log patterns (clustered log templates) with counts against the previous window of the same length. Only |
| count_observability_logsA | Count logs matching a Logs explorer query, grouped by |
| list_on_call_rolesC | List On-Call Roles |
| create_on_call_roleD | Creates a new On-Call Role from provided data |
| get_on_call_roleB | Retrieves a specific On-Call Role by id |
| update_on_call_roleC | Update a specific On-Call Role by id |
| list_on_call_shadowsC | List shadow shifts for schedule |
| create_on_call_shadowC | Creates a new on call shadow configuration from provided data |
| get_on_call_shadowA | Retrieves a specific On Call Shadow configuration by ID |
| update_on_call_shadowC | Update a specific on call shadow configuration by id |
| list_override_shiftsD | List override shifts |
| create_override_shiftB | Creates a new override shift from provided data. If any existing override shifts overlap with the specified time range, they will be automatically deleted and replaced by the new override. This endpoint is idempotent: re-sending an identical override (same user and same start/end time) returns the existing override with a 200 status and does not recreate it. |
| get_override_shiftA | Retrieves a specific override shift by id |
| update_override_shiftC | Update a specific override shift by id |
| get_playbook_taskC | Retrieves a specific playbook_task by id |
| update_playbook_taskC | Update a specific playbook task by id |
| list_playbooksD | List playbooks |
| create_playbookC | Creates a new playbook from provided data |
| get_playbookC | Retrieves a specific playbook by id |
| update_playbookC | Update a specific playbook by id |
| list_pulsesD | List pulses |
| create_pulseC | Creates a new pulse from provided data |
| get_pulseA | Retrieves a specific pulse by id |
| update_pulseC | Update a specific pulse by id |
| get_retrospective_process_groupC | Retrieves a specific Retrospective Process Group by id |
| update_retrospective_process_groupC | Update a specific Retrospective Process Group by id |
| list_retrospective_processesC | List retrospective processes |
| create_retrospective_processC | Creates a new retrospective process from provided data |
| get_retrospective_processC | Retrieves a specific retrospective process by id |
| update_retrospective_processC | Updates a specific retrospective process by id |
| get_retrospective_stepB | Retrieves a specific retrospective step by id |
| update_retrospective_stepC | Update a specific retrospective step by id |
| list_schedule_rotation_active_daysD | List schedule rotation active days |
| create_schedule_rotation_active_dayC | Creates a new schedule rotation active day from provided data |
| list_schedule_rotation_usersC | List schedule rotation users |
| create_schedule_rotation_userC | Creates a new schedule rotation user from provided data |
| list_schedule_rotationsD | List schedule rotations |
| create_schedule_rotationC | Creates a new schedule rotation from provided data |
| get_schedule_rotationC | Retrieves a specific schedule rotation by id |
| update_schedule_rotationC | Update a specific schedule rotation by id |
| list_schedulesD | List schedules |
| create_scheduleC | Creates a new schedule from provided data |
| get_scheduleC | Retrieves a specific schedule by id |
| update_scheduleC | Updates a specific schedule by id |
| list_servicesD | List services |
| create_serviceC | Creates a new service from provided data |
| get_serviceC | Retrieves a specific service by id |
| update_serviceC | Update a specific service by id |
| get_service_incidents_chartC | Get service incidents chart |
| get_service_uptime_chartC | Get service uptime chart |
| list_severitiesD | List severities |
| create_severityC | Creates a new severity from provided data |
| get_severityB | Retrieves a specific severity by id |
| update_severityC | Update a specific severity by id |
| list_shift_coverage_requestsB | List active shift coverage requests for a schedule. |
| get_shift_coverage_requestC | Retrieves a specific shift coverage request. |
| list_status_page_templatesC | List status page templates |
| create_status_page_templateC | Creates a new template from provided data |
| get_status_page_templateB | Retrieves a specific status_page_template by id |
| update_status_page_templateC | Update a specific template event by id |
| list_status_pagesD | List status pages |
| create_status_pageC | Creates a new status page from provided data |
| get_status_pageC | Retrieves a specific status page by id |
| update_status_pageC | Update a specific status page by id |
| list_sub_statusesD | List Sub-Statuses |
| create_sub_statusC | Creates a new Sub-Status from provided data |
| get_sub_statusC | Retrieves a specific Sub-Status by id |
| update_sub_statusC | Update a specific Sub-Status by id |
| list_teamsD | List teams |
| create_teamC | Creates a new team from provided data |
| get_teamC | Retrieves a specific team by id |
| update_teamC | Update a specific team by id |
| get_team_incidents_chartC | Get team incidents chart |
| get_user_email_addressesB | Retrieves all email addresses for the specified user |
| create_user_email_addressC | Creates a new user email address from provided data |
| list_user_notification_rulesC | List user notification rules |
| create_user_notification_ruleC | Creates a new user notification rule from provided data |
| get_user_phone_numbersA | Retrieves all phone numbers for the specified user |
| create_user_phone_numberC | Creates a new user phone number from provided data |
| list_usersD | List users |
| get_current_userC | Get current user |
| get_userC | Retrieves a specific user by id |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| list_incidents_resource | List recent incidents as an MCP resource for quick reference. |
| get_oncall_status_resource | Show current on-call status across teams - critical for incident response context. |
| get_workflow_guide_resource | Provide workflow guidance for common Rootly operations. |
TDQS
Scored across 282 tools
With 282 tools there is heavy overlap: list_incidents vs search_incidents vs collect_incidents vs find_related_incidents, list_shifts vs get_schedule_shifts vs get_oncall_schedule_summary, update_alert_route vs patch_alert_route, list_alert_routes vs list_alert_routing_rules, and several escalation_level/escalation_level_paths/escalation_path variants. Some descriptions do explicit disambiguation work ("use this instead of list_shifts"), which keeps it from scoring 1, but an agent still faces many near-identical choices across a huge surface.
The dominant pattern is verb_noun snake_case (create_/get_/list_/update_), consistent across most resources. However there are many deviations: patch_alert_route alongside update_alert_route, and verbless or purpose-style names like acknowledge_alert, resolve_alert, attach_alert, find_related_incidents, suggest_solutions, start_investigation, check_responder_availability, collect_incidents, search_incidents. Readable, but not one predictable convention.
282 tools is far beyond what an agent can select from reliably, and the surface mixes thin auto-generated CRUD wrappers (form_field_placement_conditions, schedule_rotation_active_days) with curated high-value tools. This is an extreme mismatch for MCP tool selection; the curated subset alone would be a well-scoped server.
Read and create/update coverage is broad across incidents, on-call, workflows, alerts, catalogs, and retrospectives, but there are essentially no delete operations anywhere in the surface, so lifecycle coverage is incomplete for nearly every resource. Agents can work around this (many deletes are admin-only), but it is a notable structural gap.