Back to Directory/Developer Tools

Rootly

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

Developer ToolsPythonv2.2.4
View on GitHub

Rootly MCP Server

PyPI version PyPI - Downloads Python Version Install MCP Server

An MCP server for the Rootly API for Cursor, Windsurf, Claude, and other MCP clients.

Demo GIF

Quick Start

Use the hosted MCP server. No local installation required.

Hosted Transport Options

  • Streamable HTTP (recommended): https://mcp.rootly.com/mcp
  • SSE (fallback): https://mcp.rootly.com/sse
  • Code Mode: https://mcp.rootly.com/mcp-codemode

General Remote Setup

Default remote config (HTTP streamable):

json
{
  "mcpServers": {
    "rootly": {
      "url": "https://mcp.rootly.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_ROOTLY_API_TOKEN"
      }
    }
  }
}

SSE fallback:

json
{
  "mcpServers": {
    "rootly": {
      "url": "https://mcp.rootly.com/sse",
      "headers": {
        "Authorization": "Bearer YOUR_ROOTLY_API_TOKEN"
      }
    }
  }
}

Code Mode:

json
{
  "mcpServers": {
    "rootly": {
      "url": "https://mcp.rootly.com/mcp-codemode",
      "headers": {
        "Authorization": "Bearer YOUR_ROOTLY_API_TOKEN"
      }
    }
  }
}

Agent Setup

<details> <summary><strong>Claude Code</strong></summary>

Streamable HTTP

bash
claude mcp add --transport http rootly https://mcp.rootly.com/mcp \
  --header "Authorization: Bearer YOUR_ROOTLY_API_TOKEN"

Code Mode:

bash
claude mcp add rootly-codemode --transport http https://mcp.rootly.com/mcp-codemode \
  --header "Authorization: Bearer YOUR_ROOTLY_API_TOKEN"

SSE fallback:

bash
claude mcp add --transport sse rootly-sse https://mcp.rootly.com/sse \
  --header "Authorization: Bearer YOUR_ROOTLY_API_TOKEN"

Manual Configuration

Create .mcp.json in your project root:

json
{
  "mcpServers": {
    "rootly": {
      "type": "sse",
      "url": "https://mcp.rootly.com/sse",
      "headers": {
        "Authorization": "Bearer YOUR_ROOTLY_API_TOKEN"
      }
    }
  }
}

Restart Claude Code after updating the config.

</details> <details> <summary><strong>Gemini CLI</strong></summary>

Install the extension:

bash
gemini extensions install https://github.com/Rootly-AI-Labs/Rootly-MCP-server

Or configure manually in ~/.gemini/settings.json:

json
{
  "mcpServers": {
    "rootly": {
      "command": "uvx",
      "args": ["--from", "rootly-mcp-server", "rootly-mcp-server"],
      "env": {
        "ROOTLY_API_TOKEN": "<YOUR_ROOTLY_API_TOKEN>"
      }
    }
  }
}
</details> <details> <summary><strong>Cursor</strong></summary>

Add to .cursor/mcp.json or ~/.cursor/mcp.json:

json
{
  "mcpServers": {
    "rootly": {
      "url": "https://mcp.rootly.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_ROOTLY_API_TOKEN>"
      }
    }
  }
}
</details> <details> <summary><strong>Windsurf</strong></summary>

Add to ~/.codeium/windsurf/mcp_config.json:

json
{
  "mcpServers": {
    "rootly": {
      "serverUrl": "https://mcp.rootly.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_ROOTLY_API_TOKEN>"
      }
    }
  }
}
</details> <details> <summary><strong>Codex</strong></summary>

Add to ~/.codex/config.toml:

toml
[mcp_servers.rootly]
url = "https://mcp.rootly.com/mcp"
bearer_token_env_var = "ROOTLY_API_TOKEN"
</details> <details> <summary><strong>Claude Desktop</strong></summary>

Add to claude_desktop_config.json:

json
{
  "mcpServers": {
    "rootly": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.rootly.com/mcp",
        "--header",
        "Authorization: Bearer <YOUR_ROOTLY_API_TOKEN>"
      ]
    }
  }
}
</details>

Rootly CLI

Standalone CLI for incidents, alerts, services, and on-call operations.

Install via Homebrew:

bash
brew install rootlyhq/tap/rootly-cli

Or via Go:

bash
go install github.com/rootlyhq/rootly-cli/cmd/rootly@latest

For more details, see the Rootly CLI repository.

Alternative Installation (Local)

Run the MCP server locally if you do not want to use the hosted service.

Prerequisites

  • Python 3.12 or higher
  • uv package manager
    bash
    curl -LsSf https://astral.sh/uv/install.sh | sh
  • Rootly API token

API Token Types

Choose the token type based on the access you need:

  • Global API Key: Full access across the Rootly instance. Best for organization-wide visibility.
  • Team API Key: Access limited to entities owned by that team.
  • Personal API Key: Access matches the user who created it.

A Global API Key is recommended for tools like get_oncall_handoff_summary, get_oncall_shift_metrics, and org-wide incident search.

With uv

json
{
  "mcpServers": {
    "rootly": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "--from",
        "rootly-mcp-server",
        "rootly-mcp-server"
      ],
      "env": {
        "ROOTLY_API_TOKEN": "<YOUR_ROOTLY_API_TOKEN>"
      }
    }
  }
}

Self-Hosted Transport Options

Choose one transport per server process:

  • Streamable HTTP endpoint path: /mcp
  • SSE endpoint path: /sse
  • Code Mode (experimental) endpoint path: /mcp-codemode in hosted dual-transport mode

Example Docker run (Streamable HTTP):

bash
docker run -p 8000:8000 \
  -e ROOTLY_TRANSPORT=streamable-http \
  -e ROOTLY_API_TOKEN=<YOUR_ROOTLY_API_TOKEN> \
  rootly-mcp-server

Example Docker run (SSE):

bash
docker run -p 8000:8000 \
  -e ROOTLY_TRANSPORT=sse \
  -e ROOTLY_API_TOKEN=<YOUR_ROOTLY_API_TOKEN> \
  rootly-mcp-server

Example Docker run (Dual transport + Code Mode):

bash
docker run -p 8000:8000 \
  -e ROOTLY_TRANSPORT=both \
  -e ROOTLY_API_TOKEN=<YOUR_ROOTLY_API_TOKEN> \
  rootly-mcp-server

With uvx

json
{
  "mcpServers": {
    "rootly": {
      "command": "uvx",
      "args": [
        "--from",
        "rootly-mcp-server",
        "rootly-mcp-server"
      ],
      "env": {
        "ROOTLY_API_TOKEN": "<YOUR_ROOTLY_API_TOKEN>"
      }
    }
  }
}

Features

  • Dynamic Tool Generation: Automatically creates MCP resources from Rootly's OpenAPI (Swagger) specification
  • Smart Pagination: Defaults to 10 items per request for incident endpoints to prevent context window overflow
  • API Filtering: Limits exposed API endpoints for security and performance
  • Intelligent Incident Analysis: Smart tools that analyze historical incident data
    • find_related_incidents: Uses TF-IDF similarity analysis to find historically similar incidents
    • suggest_solutions: Mines past incident resolutions to recommend actionable solutions
  • MCP Resources: Exposes incident and team data as structured resources for easy AI reference
  • Intelligent Pattern Recognition: Automatically identifies services, error types, and resolution patterns
  • On-Call Health Integration: Detects workload health risk in scheduled responders

Supported Tools

The default server configuration exposes 101 tools.

Custom Agentic Tools

  • check_oncall_health_risk
  • check_responder_availability
  • create_override_recommendation
  • find_related_incidents
  • getIncident - retrieve a single incident for direct verification, including PIR-related fields
  • get_alert_by_short_id
  • get_oncall_handoff_summary
  • get_oncall_schedule_summary
  • get_oncall_shift_metrics
  • get_server_version
  • get_shift_incidents
  • list_endpoints
  • list_shifts
  • search_incidents
  • suggest_solutions
  • updateIncident - scoped incident update tool for summary and retrospective_progress_status

OpenAPI-Generated Tools

text
attachAlert
createAlert
createEnvironment
createEscalationLevel
createEscalationLevelPaths
createEscalationPath
createEscalationPolicy
createFunctionality
createIncidentActionItem
createIncidentType
createOnCallRole
createOnCallShadow
createOverrideShift
createSchedule
createScheduleRotation
createScheduleRotationActiveDay
createScheduleRotationUser
createService
createSeverity
createTeam
createWorkflow
deleteEscalationLevel
deleteEscalationPath
deleteEscalationPolicy
deleteSchedule
deleteScheduleRotation
getAlert
getCurrentUser
getEnvironment
getEscalationLevel
getEscalationPath
getEscalationPolicy
getFunctionality
getIncidentType
getOnCallRole
getOnCallShadow
getOverrideShift
getSchedule
getScheduleRotation
getScheduleShifts
getService
getSeverity
getTeam
getUser
getWorkflow
listAlerts
listEnvironments
listEscalationLevels
listEscalationLevelsPaths
listEscalationPaths
listEscalationPolicies
listFunctionalities
listIncidentActionItems
listIncidentAlerts
listIncident_Types
listOnCallRoles
listOnCallShadows
listOverrideShifts
listScheduleRotationActiveDays
listScheduleRotationUsers
listScheduleRotations
listSchedules
listServices
listSeverities
listShifts
listTeams
listUsers
listWorkflows
updateAlert
updateEnvironment
updateEscalationLevel
updateEscalationPath
updateEscalationPolicy
updateFunctionality
updateIncidentType
updateOnCallRole
updateOnCallShadow
updateOverrideShift
updateSchedule
updateScheduleRotation
updateService
updateSeverity
updateTeam
updateUser
updateWorkflow

Delete operations are intentionally scoped to screenshot coverage paths: deleteSchedule, deleteScheduleRotation, deleteEscalationPolicy, deleteEscalationPath, deleteEscalationLevel.

On-Call Health Integration

Integrates with On-Call Health to detect workload health risk in scheduled responders.

Setup

Set the ONCALLHEALTH_API_KEY environment variable:

json
{
  "mcpServers": {
    "rootly": {
      "command": "uvx",
      "args": ["rootly-mcp-server"],
      "env": {
        "ROOTLY_API_TOKEN": "your_rootly_token",
        "ONCALLHEALTH_API_KEY": "och_live_your_key"
      }
    }
  }
}

Usage

text
check_oncall_health_risk(
    start_date="2026-02-09",
    end_date="2026-02-15"
)

Returns at-risk users who are scheduled, recommended safe replacements, and action summaries.

Example Skills

Pre-built Claude Code skills:

🚨 Rootly Incident Responder

This skill:

  • Analyzes production incidents with full context
  • Finds similar historical incidents using ML-based similarity matching
  • Suggests solutions based on past successful resolutions
  • Coordinates with on-call teams across timezones
  • Correlates incidents with recent code changes and deployments
  • Creates action items and remediation plans
  • Provides confidence scores and time estimates

Quick Start:

bash
# Copy the skill to your project
mkdir -p .claude/skills
cp examples/skills/rootly-incident-responder.md .claude/skills/

# Then in Claude Code, invoke it:
# @rootly-incident-responder analyze incident #12345

It demonstrates a full incident response workflow using Rootly tools and GitHub context.

On-Call Shift Metrics

Get on-call shift metrics for any time period, grouped by user, team, or schedule. Includes primary/secondary role tracking, shift counts, hours, and days on-call.

text
get_oncall_shift_metrics(
    start_date="2025-10-01",
    end_date="2025-10-31",
    group_by="user"
)

On-Call Handoff Summary

Complete handoff: current/next on-call + incidents during shifts.

python
# All on-call (any timezone)
get_oncall_handoff_summary(
    team_ids="team-1,team-2",
    timezone="America/Los_Angeles"
)

# Regional filter - only show APAC on-call during APAC business hours
get_oncall_handoff_summary(
    timezone="Asia/Tokyo",
    filter_by_region=True
)

Regional filtering shows only people on-call during business hours (9am-5pm) in the specified timezone.

Returns: schedules with current_oncall, next_oncall, and shift_incidents

Shift Incidents

Incidents during a time period, with filtering by severity/status/tags.

python
get_shift_incidents(
    start_time="2025-10-20T09:00:00Z",
    end_time="2025-10-20T17:00:00Z",
    severity="critical",  # optional
    status="resolved",    # optional
    tags="database,api"   # optional
)

Returns: incidents list + summary (counts, avg resolution time, grouping)

Contributing

See CONTRIBUTING.md for developer setup and guidelines.

Play with it on Postman

<img src="https://run.pstmn.io/button.svg" alt="Run In Postman" style="width: 128px; height: 32px;">

About Rootly AI Labs

This project was developed by Rootly AI Labs, where we're building the future of system reliability and operational excellence. As an open-source incubator, we share ideas, experiment, and rapidly prototype solutions that benefit the entire community. Rootly AI logo

Learn More

Best MCP Servers for DevOps: GitHub, Docker, CloudflareMCPFind indexes 3,141 devtools MCP servers and 164 cloud servers, making DevOps one of the richest categories in the directory. We analyzed both to surface the strongest options for CI/CD automation, container management, and cloud infrastructure operations.Read articleHow to Set Up MCP Servers in JetBrains IDEs (2026 Guide)JetBrains IDEs added MCP support through their AI Assistant plugin, giving IntelliJ IDEA, WebStorm, PyCharm, and GoLand users access to the same MCP server ecosystem as Cursor and VS Code. This guide covers how to configure MCP in JetBrains, which devtools servers work well, and how the experience compares to other MCP-enabled IDEs.Read articleHow to Deploy an MCP Server with DockerMost MCP servers fail in production because they depend on local system state that Docker eliminates. This guide shows how to write Dockerfiles for Node.js and Python MCP servers, expose the right ports, and push to a container registry for reliable remote deployment.Read article