Rootly
Manage incidents from your IDE. An MCP server allowing to pull out incidents and their associated metadata using Rootly API.
What is Rootly?
Rootly is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to manage incidents from your ide. an mcp server allowing to pull out incidents and their associated metadata using rootly api.
Manage incidents from your IDE. An MCP server allowing to pull out incidents and their associated metadata using Rootly API.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Manage incidents from your IDE. An MCP server allowing to pu
Use Cases
Maintainer
Works with
Installation
NPM
npx -y rootly-mcp-serverPIP
pip install rootly-mcp-serverManual Installation
npx -y rootly-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Rootly
The Rootly MCP server gives AI assistants direct access to your Rootly incident management platform, exposing 218 tools (70 in slim profile) for listing incidents, retrieving metadata, finding historically similar incidents, suggesting solutions from past resolutions, and monitoring on-call health. It integrates with the Rootly API using your API token and supports both read-only and write operations, making it possible to investigate and manage active incidents entirely from within your IDE or AI chat interface.
Prerequisites
- Python 3.9+ with pip or uv/uvx installed, or access to the Rootly CLI via Homebrew
- A Rootly account with an API token (generate at app.rootly.com under Profile > API Tokens)
- An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
Obtain your Rootly API token
Log in to your Rootly account, navigate to your Profile settings, and generate a new API token. Copy the token — you will need it in the configuration step.
Install the Rootly MCP server
Install via pip or use uvx for an isolated run without a permanent install. The uvx method is recommended to avoid dependency conflicts.
pip install rootly-mcp-server
# or, without installing:
uvx --from rootly-mcp-server rootly-mcp-serverAdd the server to your MCP client configuration
Edit your MCP client configuration file to add the Rootly server with your API token. Use uvx for isolated execution or reference the installed script directly.
{
"mcpServers": {
"rootly": {
"command": "uvx",
"args": ["--from", "rootly-mcp-server", "rootly-mcp-server"],
"env": {
"ROOTLY_API_TOKEN": "YOUR_ROOTLY_API_TOKEN",
"ROOTLY_MCP_ENABLE_WRITE_TOOLS": "false"
}
}
}
}Enable write tools if needed
By default only read tools are enabled. To allow incident creation and updates, set ROOTLY_MCP_ENABLE_WRITE_TOOLS to true. You can also restrict which tools are available using ROOTLY_MCP_ENABLED_TOOLS.
"ROOTLY_MCP_ENABLE_WRITE_TOOLS": "true",
"ROOTLY_MCP_ENABLED_TOOLS": "list_incidents,get_incident,find_related_incidents,suggest_solutions"Restart your MCP client and verify
Restart Claude Desktop or your IDE. Ask your AI assistant to list recent incidents to confirm the connection is working.
Rootly Examples
Client configuration
Example claude_desktop_config.json for connecting to Rootly with read-only access.
{
"mcpServers": {
"rootly": {
"command": "uvx",
"args": ["--from", "rootly-mcp-server", "rootly-mcp-server"],
"env": {
"ROOTLY_API_TOKEN": "YOUR_ROOTLY_API_TOKEN",
"ROOTLY_MCP_ENABLE_WRITE_TOOLS": "false"
}
}
}
}Prompts to try
Example prompts for incident investigation and on-call management.
- "List all critical incidents from the past 7 days and summarize their root causes."
- "Find incidents similar to incident #12345 and suggest solutions based on past resolutions."
- "Show me the current on-call schedule and any active incidents assigned to the on-call team."
- "What is the on-call health risk for the SRE team this week?"
- "Get the handoff summary for the next on-call shift."Troubleshooting Rootly
Authentication errors or 401 responses from the Rootly API
Verify that ROOTLY_API_TOKEN is set to a valid, active token from your Rootly profile. Tokens can be revoked; regenerate one at app.rootly.com if needed. Ensure there are no leading/trailing spaces in the token value.
Write tools are not appearing or incident creation fails
Set ROOTLY_MCP_ENABLE_WRITE_TOOLS to 'true' in the env block. Without this flag only read tools are exposed. Also confirm your API token has write permissions in Rootly.
Too many tools causing slow responses or context issues
Use ROOTLY_MCP_ENABLED_TOOLS to restrict to a comma-separated list of specific tools you need, or set ROOTLY_MCP_HOSTED_TOOL_PROFILE to 'slim' to reduce from 218 to 70 tools.
Frequently Asked Questions about Rootly
What is Rootly?
Rootly is a Model Context Protocol (MCP) server that manage incidents from your ide. an mcp server allowing to pull out incidents and their associated metadata using rootly api. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Rootly?
Install via npm with the command: npx -y rootly-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Rootly?
Rootly works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Rootly free to use?
Yes, Rootly is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Rootly Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Rootly? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Rootly in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Rootly?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.