Model Context Protocol moderate risk

Rootly

The Rootly MCP server allows users to manage incident response directly from their IDE by leveraging Rootly's API for incident management, on-call scheduling, and resolution.

Connections & Capabilities

Connects To

GitHub

Capabilities

readwrite

Quickstart

Config

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

Exposed MCP Tools (6)

safe

find_related_incidents

Finds historically similar incidents using TF-IDF similarity analysis.

Read-only operation; retrieves incident data for analysis.

safe

suggest_solutions

Recommends actionable solutions by mining past incident resolutions.

Read-only operation; analyzes past resolutions to provide suggestions.

safe

get_oncall_shift_metrics

Retrieves on-call shift metrics for a specified time period, grouped by user, team, or schedule.

Read-only operation; fetches metrics without modifying data.

safe

get_oncall_handoff_summary

Provides a summary of the current and next on-call personnel, along with incidents during their shifts.

Read-only operation; gathers on-call information and incident summaries.

safe

get_shift_incidents

Lists incidents during a specified time period, with filtering options for severity, status, and tags.

Read-only operation; retrieves incident lists based on specified filters.

safe

check_oncall_health_risk

Detects workload health risk in scheduled responders.

Read-only operation; analyzes on-call health data.

Safety Assessment

The Rootly MCP server offers convenient incident management from within an IDE. It is relatively safe for read-only operations. However, write operations should be performed with caution, ensuring the API key has appropriate, limited permissions to prevent unintended consequences.

API key authentication
Dynamic tool generation limits exposed API endpoints
Smart pagination prevents context window overflow
Read and write operations are available, but require explicit tool invocation

Requires an API key with potentially broad permissions
No built-in sandboxing
Potential for unintended modifications if API key is misconfigured
Exposure to Rootly API vulnerabilities