Rootly MCP Server for Claude
Manage production incidents from Claude — create incidents, check on-call schedules, find related past incidents, suggest solutions, track post-mortems, and orchestrate response workflows — with the official Rootly remote MCP server.
Open the source and read safety notes before installing.
Safety notes
- The MCP server can create and update production incidents — review Claude's proposed actions before confirming write operations during live incidents.
- Security-sensitive operations and bulk deletions are excluded from the default tool set; the hosted endpoint returns approximately 70 frequently-used tools in 'slim' mode.
- A Global API Key is recommended for full cross-team visibility; team-scoped keys may return incomplete results for on-call and analytics tools.
Privacy notes
- Incident details, on-call schedules, escalation policies, team configurations, and post-incident review data from your Rootly workspace are surfaced in Claude's context.
- OAuth is the recommended authentication method — no API token is stored in your MCP configuration.
Prerequisites
- A Rootly account — authenticate via OAuth when prompted, or generate an API key in Rootly → Account → Manage API Keys.
- An MCP client such as Claude Code or Claude Desktop.
Schema details
- Install type
- cli
- Troubleshooting
- No
- Scope
- Source repo
- Estimated setup
- 5 minutes
- Difficulty
- beginner
- Website
- https://rootly.com
Full copyable content
{
"mcpServers": {
"rootly": {
"type": "http",
"url": "https://mcp.rootly.com/mcp"
}
}
}About this resource
Overview
The Rootly MCP Server is the official remote Model Context Protocol server from Rootly AI Labs. It connects Claude directly to your Rootly incident management workspace — giving you natural-language access to incident creation, on-call schedules, escalation policies, playbooks, runbooks, post-incident reviews, and intelligent incident correlation.
With 200+ tools (or the hosted slim profile of ~70 frequently-used tools), the server covers the full incident lifecycle from detection through review.
Authentication uses OAuth (recommended) or a Rootly API token for programmatic access.
Key capabilities
- Incident management — create incidents, update status, add action items, and close incidents.
- On-call analytics — query on-call shift metrics, get handoff summaries, check current coverage.
- Intelligent matching — find related past incidents by symptom and suggest solutions from prior runbooks.
- Escalation policies — list and inspect escalation chains and alert routing.
- Schedules & teams — view on-call schedules, override rotations, list team members.
- Playbooks & workflows — trigger incident workflows and playbooks from natural language.
- Post-incident reviews — track and draft post-mortem documents.
- Dashboards — pull incident metrics and reliability dashboards.
How it compares
| Server | Incident lifecycle | On-call analytics | AI matching | Post-mortems | Auth |
|---|---|---|---|---|---|
| Rootly MCP | Yes | Yes | Yes | Yes | OAuth / API key |
| PagerDuty MCP | Yes | Yes | No | Limited | API key |
| Opsgenie MCP | Yes | Limited | No | No | API key |
| FireHydrant MCP | Yes | Limited | No | Yes | API key |
Rootly's MCP is notable for the AI-powered find_related_incidents and suggest_solutions tools,
which use semantic matching against incident history — not just keyword search.
Installation
Claude Code (OAuth — recommended)
claude mcp add --transport http rootly https://mcp.rootly.com/mcp
Run /mcp in Claude Code to authenticate via OAuth.
Claude Code (API token)
claude mcp add --transport http rootly https://mcp.rootly.com/mcp \
--header "Authorization: Bearer YOUR_ROOTLY_API_TOKEN"
Generate a Global API Key in Rootly → Account → Manage API Keys for full functionality.
Claude Desktop
{
"mcpServers": {
"rootly": {
"type": "http",
"url": "https://mcp.rootly.com/mcp"
}
}
}
Alternative endpoints
| Endpoint | URL |
|---|---|
| Streamable HTTP (recommended) | https://mcp.rootly.com/mcp |
| SSE (stable fallback) | https://mcp.rootly.com/sse |
| Code mode | https://mcp.rootly.com/mcp-codemode |
Requirements
- A Rootly account with appropriate team access.
- An MCP client (Claude Code or Claude Desktop).
Security
- OAuth authentication minimizes credential exposure.
- Security-sensitive operations and deletions are excluded from the default tool set.
- Use a Global API Key for full visibility; team-scoped keys limit cross-team data access.
Source Verification Notes
Verified on 2026-06-18:
- Rootly's MCP documentation at
docs.rootly.com/integrations/mcp-serverconfirms the hosted endpoint, OAuth + API token auth, 200+ tools, and the slim profile (~70 tools). - Rootly's launch blog at
rootly.com/blog/introducing-the-rootly-mcp-serverdocuments the AI-matching tools (find_related_incidents,suggest_solutions) and the incident lifecycle scope. - GitHub repo
Rootly-AI-Labs/Rootly-MCP-server(Apache-2.0) is the open-source reference implementation.
Source citations
Add this badge to your README
How it compares
Rootly MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Rootly MCP Server for Claude Manage production incidents from Claude — create incidents, check on-call schedules, find related past incidents, suggest solutions, track post-mortems, and orchestrate response workflows — with the official Rootly remote MCP server. Open dossier | ConfigCat MCP Server for Claude Manage ConfigCat feature flags from Claude — create, update, and delete flags and targeting rules, manage environments, find and clean up stale flags, and audit change history — with the official ConfigCat MCP server and its 52 tools for the full ConfigCat Management API. Open dossier | Fly.io MCP Server for Claude Manage Fly.io applications, machines, volumes, secrets, certificates, and organizations from Claude — with the official Fly.io MCP server built into the flyctl CLI. Open dossier | LaunchDarkly MCP Server for Claude Manage LaunchDarkly feature flags, AI configs, environments, and audit logs from Claude — with the official LaunchDarkly Model Context Protocol server backed by the LaunchDarkly REST API. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | mcp | mcp | mcp | mcp |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | Rootly AI Labs | ConfigCat | Fly.io | LaunchDarkly |
| Added | 2026-06-18 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | Claude CodeCodexCursorClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop |
| Source repo | — | — | — | — |
| Safety notes | ✓The MCP server can create and update production incidents — review Claude's proposed actions before confirming write operations during live incidents. Security-sensitive operations and bulk deletions are excluded from the default tool set; the hosted endpoint returns approximately 70 frequently-used tools in 'slim' mode. A Global API Key is recommended for full cross-team visibility; team-scoped keys may return incomplete results for on-call and analytics tools. | ✓Tools can create, update, and delete feature flags, targeting rules, environments, and segments — changes affect live feature flag configuration. Use `list-staleflags` before deleting flags to identify zombie flags and avoid breaking active SDKs. | ✓The Fly.io MCP server runs locally with full access to your authenticated Fly.io account — it can create, delete, and modify apps, machines, and secrets. Fly.io warns that running the server remotely can give others access to run commands on your behalf; keep it bound to localhost unless you intend remote access. Destructive operations (machine deletion, secret updates) are available — review Claude's proposed commands before executing in production environments. | ✓Feature flag operations include create, update (patch), and delete — changes affect live targeting rules for all users in the environment. Audit log and code reference reads are non-destructive, but flag patch and delete operations are irreversible and will affect production traffic immediately. Scope the API key to the minimum required permissions (read-only for analysis workflows, write only for flag management workflows). |
| Privacy notes | ✓Incident details, on-call schedules, escalation policies, team configurations, and post-incident review data from your Rootly workspace are surfaced in Claude's context. OAuth is the recommended authentication method — no API token is stored in your MCP configuration. | ✓Feature flag configurations, targeting rules, audience segments, SDK keys, and audit log entries from your ConfigCat account are surfaced in Claude's context. `CONFIGCAT_API_USER` and `CONFIGCAT_API_PASS` are Management API credentials — keep them in the MCP config env and never commit them to version control. | ✓App names, machine IDs, secret names (not values unless explicitly requested), and log content may be surfaced into Claude's context. Fly.io API tokens (`FLY_ACCESS_TOKEN`) grant full account access — store them in your environment, not in repositories. | ✓Feature flag definitions, targeting rules, user segments, AI config prompts, environment configurations, and audit log entries from your LaunchDarkly project are surfaced in Claude's context. Your API key is passed as a CLI argument — store it in Claude Code's MCP config rather than in shell history; rotate keys from the LaunchDarkly Authorization page. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.