Connector guide9-minute read40 MCP tools7 languages

How to Connect Rootly to Claude via MCP

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

HCBy HelpCode teamUpdated 9 min read Open-source on GitHub

No credit card · 7-day trial · Self-host alternative available

Rootly

Rootly

Rootly incident management: incidents with timeline, action items and status page updates, alerts, services, functionalities, teams, severities and incident types, on-call (who is on call, schedules, shifts, escalation policies), status pages and retrospectives. Declare, update, mitigate and resolve incidents, acknowledge and resolve alerts.

tools

40

Region

INTL

Category

Monitoring

Authentication

Bearer Token

Required env vars

ROOTLY_API_KEY
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Skip the install. Get this working in under 2 minutes.

Start a free trial on cloud.anythingmcp.com, add the Rootly in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.

Start free trial

AnythingMCP is listed in Claude's connector directory: add it to Claude in one click (opens in a new tab), then sign in and choose which MCP servers Claude may use.

Summary

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

Try asking

Example prompts for Rootly

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

Rootly · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Rootly, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Rootly + Claude

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

ROOTLY_API_KEY

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a Rootly account.

  1. In Rootly open the organization menu, then Organization Settings, API Keys, and create a key. A Global key sees the whole organization, a Team key only that team's records, a Personal key acts with your own permissions.
  2. Give the key a role that can read what you need, plus write permission for incidents, alerts and action items if the AI should change them.
  3. Paste only the key, without Bearer in front, into ROOTLY_API_KEY and run rootly_get_current_user. It shows the user the key acts as; a Global or Team key answers with the user who created it.

What is going on: rootly_list_incidents with status: "started,mitigated" (or in_triage) lists the current incidents; filters cover severity, service, team, environment, type, free text and dates. rootly_get_incident shows one incident with all its attributes, rootly_list_incident_events its timeline and rootly_list_incident_action_items its tasks. To find ids the AI uses rootly_list_severities, rootly_list_services, rootly_get_service, rootly_list_functionalities, rootly_get_functionality, rootly_list_teams, rootly_get_team, rootly_list_environments, rootly_list_incident_types and rootly_list_users.

Running an incident: rootly_create_incident declares one. With an idempotency_key a retry within 24 hours returns the same incident instead of a second one; kind test is for a try. rootly_update_incident changes title, summary, severity, services, teams, labels or status; a list replaces the whole list. rootly_add_incident_event adds internal or external timeline notes, rootly_mitigate_incident and rootly_resolve_incident move the incident on with a short note. Action items: rootly_list_action_items across all incidents, rootly_get_action_item, rootly_create_action_item and rootly_update_action_item (for example status done).

Alerts: rootly_list_alerts (for example status triggered or open), rootly_get_alert with the raw payload the source sent, rootly_acknowledge_alert (the escalation stops paging the next level) and rootly_resolve_alert, which can also resolve the incidents the alert is attached to.

On-call: rootly_list_oncalls answers who is on call now or in a time window. rootly_list_schedules, rootly_get_schedule, rootly_get_schedule_shifts, rootly_list_shifts and rootly_list_escalation_policies give the details.

Status pages and retrospectives: rootly_list_status_pages, rootly_get_status_page and rootly_list_incident_status_page_events read; rootly_create_status_page_event publishes an update (investigating, identified, monitoring, resolved). rootly_list_retrospectives and rootly_get_retrospective read the post-mortems.

Before writing: a normal incident runs workflows, opens a Slack channel and can page people; a status page update is public and can e-mail the subscribers. So the AI shows you what it is about to do and waits for your yes. A private incident cannot be made public again.

Switched off at install: no tool. Everything is on from the start; what the AI may do is limited by the role and team of the key.

Data formats: answers follow JSON:API: records are in data (id, type, attributes, relationships), records embedded with include in included. Ids are UUIDs, user ids are numbers. The human incident number is attributes.sequential_id (INC-123). Times are ISO 8601, in UTC unless a time zone is given. rootly_list_incidents and rootly_list_alerts return a compact set of attributes by default; fields: "" returns all of them. Zoom meeting passwords and host links are left out of incident answers.

Paging: lists return meta with current_page, next_page (null on the last page), total_count and total_pages; the AI calls again with page_number. Incidents and alerts also accept the cursor page_after from meta.next_cursor. page_size goes up to 100, but small pages work better because Rootly records are large.

Common errors: 401 means a wrong or revoked key, 403 a key whose role or team does not allow the call, 404 an unknown id or one outside the key's team, 422 a validation error whose errors name the field, 429 the rate limit (the X-RateLimit-* headers say when it resets; wait and retry).

The connector does not delete incidents, alerts or action items, does not change schedules, escalation policies or status pages and does not write retrospectives.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Claude

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Recommended path: works on claude.ai web without editing any config file.

  1. In Claude, open Customize → Connectors.
  2. Click +, then Add custom connector.
  3. Enter a name, e.g. Rootly, and the remote MCP server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID, then click Add.
  4. Click Connect and sign in to AnythingMCP (OAuth) to allow access.

All tools below appear in your chat: start typing prompts.

Available tools

ToolWhat it does
rootly_get_current_userShow the user the API key acts as: id, name, email, time zone and role
rootly_list_incidentsList incidents, newest first by default: sequential id (the 123 in INC-123), title, status, kind, severity, services, teams, environments…
rootly_get_incidentGet one incident with all its attributes: title, summary, status, severity, services, teams, environments, types, labels, Slack channel…
rootly_create_incidentDeclare an incident
rootly_update_incidentChange an incident: title, summary, status, severity, affected services, functionalities, environments, types, teams, causes or labels
rootly_mitigate_incidentMark an incident as mitigated (the impact is under control) with a short note on how
rootly_resolve_incidentMark an incident as resolved with a short note on how
rootly_list_incident_eventsList the timeline of an incident: the events (notes, status changes, updates) with their text, visibility (internal or external) and when…
rootly_add_incident_eventAdd a note to the timeline of an incident
rootly_list_action_itemsList action items across all incidents: summary, kind (task during the incident, follow_up after it), priority, status, assignee, due date…
rootly_list_incident_action_itemsList the action items of one incident: summary, kind, priority, status, assignee and due date
rootly_get_action_itemGet one action item with its description, assignee, teams, due date and linked Jira issue
rootly_create_action_itemAdd an action item to an incident: a task to do now or a follow-up for after the incident, with priority, assignee and due date
rootly_update_action_itemChange an action item: summary, description, status (e.g. done), priority, assignee or due date
rootly_list_alertsList alerts, newest first: short id, summary, status (open, triggered, acknowledged, resolved, deferred), source (datadog, grafana, email…
rootly_get_alertGet one alert with its full details, including the raw payload the source sent (data), labels, responders and linked incidents
rootly_acknowledge_alertAcknowledge an alert: someone is looking at it, so its escalation stops paging the next level
rootly_resolve_alertResolve an alert, optionally with a note and also resolving the incidents it is attached to
rootly_list_servicesList the services in the catalog: name, slug, description, owners, linked repositories and external ids (Backstage, Cortex, OpsLevel…
rootly_get_serviceGet one service with its description, owner teams and users, escalation policy, alert and incident broadcast settings and external links
rootly_list_functionalitiesList the functionalities (user-facing capabilities such as Checkout or Login) with name, slug, description and owners
rootly_get_functionalityGet one functionality with its description, owners, linked services and status page components
rootly_list_teamsList the teams (groups) with name, slug, description, members and their on-call and escalation settings
rootly_get_teamGet one team with its description and members; add include for its schedules and escalation policies
rootly_list_environmentsList the environments (production, staging and so on) with name, slug and colour
rootly_list_severitiesList the severity levels (e.g
rootly_list_incident_typesList the incident types (e.g
rootly_list_usersList the users of the organization: id, name, email, time zone; add include for role, teams or schedules
rootly_list_oncallsWho is on call: the on-call entries of every escalation policy, schedule and level for now or a time window, with the user, schedule…
rootly_list_schedulesList the on-call schedules with name, description, owning teams and time zone
rootly_get_scheduleGet one on-call schedule with its owners, time zone and settings
rootly_get_schedule_shiftsList the shifts of one schedule in a time window: who is on call from when to when, including overrides
rootly_list_shiftsList on-call shifts across schedules in a time window (default: the shifts running now): schedule, rotation, user, start and end, override…
rootly_list_escalation_policiesList the escalation policies with name, description, repeat settings and owning teams; add include for their levels and paths
rootly_list_status_pagesList the status pages with title, public URL, whether they are public, and their settings
rootly_get_status_pageGet one status page with its title, description, public URL, components and settings
rootly_list_incident_status_page_eventsList the updates an incident published to status pages: text, status (investigating, identified, monitoring, resolved), status page and time
rootly_create_status_page_eventPublish an incident update on a status page, e.g
rootly_list_retrospectivesList incident retrospectives (post-mortems): title, status (draft, published), the incident, URL and dates
rootly_get_retrospectiveGet one retrospective with its title, status, content, URL and the incident it belongs to

Example prompts

  • "Which incidents are open right now, and who is on call for the payments service?"
  • "Show me the timeline of INC-482 and list its open action items."
  • "Declare a SEV2 incident for slow checkout on the checkout service. Show me the details before you create it."
  • "Acknowledge the triggered Datadog alerts for the API gateway and tell me what they say."
  • "Post a Monitoring update for INC-482 on our status page: the fix is deployed and we are watching the error rate."

FAQ

Does it work with Claude Code as well as Claude Desktop? Yes, point both at https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID.

Next steps

Was this guide helpful?

Your Rootly agent is one click away.

Install the connector, paste the key, prompt Claude. Free for 7 days, no credit card.

Related guides

Connectors

How to Connect Rootly to ChatGPT via MCP

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

Connectors

How to Connect Rootly to Cursor via MCP

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

Connectors

How to Connect Rootly to Gemini via MCP

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

Connectors

How to Connect Rootly to Meta Muse via MCP

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

Connectors

Rootly to MCP: Incidents, Alerts, On-Call, Status Pages and Retrospectives in any AI Agent

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.

Connectors

How to Connect Rootly to Microsoft Copilot via MCP

Rootly incident management from any AI agent: declare, update, mitigate and resolve incidents with timeline notes and action items, acknowledge and resolve alerts, see who is on call, publish status page updates and read retrospectives, services, teams and severities.